CN119313660A - Dynamic detection and feature extraction method of textile spindle speed - Google Patents
Dynamic detection and feature extraction method of textile spindle speed Download PDFInfo
- Publication number
- CN119313660A CN119313660A CN202411848115.6A CN202411848115A CN119313660A CN 119313660 A CN119313660 A CN 119313660A CN 202411848115 A CN202411848115 A CN 202411848115A CN 119313660 A CN119313660 A CN 119313660A
- Authority
- CN
- China
- Prior art keywords
- image
- dynamic
- textile
- rotation
- mark
- 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
- 239000004753 textile Substances 0.000 title claims abstract description 69
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000000605 extraction Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 81
- 239000003550 marker Substances 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 18
- 238000005070 sampling Methods 0.000 claims abstract description 18
- 238000003708 edge detection Methods 0.000 claims abstract description 15
- 239000000463 material Substances 0.000 claims abstract description 12
- 238000009434 installation Methods 0.000 claims abstract description 10
- 230000000737 periodic effect Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000006399 behavior Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000002310 reflectometry Methods 0.000 claims description 8
- 238000012854 evaluation process Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000013097 stability assessment Methods 0.000 claims 2
- 230000005856 abnormality Effects 0.000 claims 1
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 11
- 238000003908 quality control method Methods 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 3
- 238000010191 image analysis Methods 0.000 abstract 1
- 238000009987 spinning Methods 0.000 description 20
- 230000002159 abnormal effect Effects 0.000 description 13
- 238000009941 weaving Methods 0.000 description 13
- 238000006073 displacement reaction Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 239000012467 final product Substances 0.000 description 2
- 238000005312 nonlinear dynamic Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
本发明公开了纺织锭速动态检测及特征提取方法，涉及纺织锭速检测技术领域，用于解决纺织锭速检测精度差的问题；本发明通过在纱管上端安装高对比度且具有周期性纹理的标记，并优化其几何形状、材质和安装角度，在高速旋转过程中图像稳定清晰，提高弱捻现象的检测精度，动态调整曝光时间和采样速率，能够在不同转速下稳定捕捉图像，克服传统方法中动态场景下的模糊和噪声问题，通过对采集图像进行去噪处理、边缘检测及旋转特征分析，有效提取动态特征，并通过标记位置匹配与稳定性评估，准确判断弱捻现象，此外，基于图像分析结果，结合生成信号调整纺织检测策略，提供即时反馈与调整，提高了生产过程中的质量控制效率和设备响应速度。
The invention discloses a method for dynamic detection and feature extraction of textile spindle speed, relates to the technical field of textile spindle speed detection, and is used to solve the problem of poor detection accuracy of textile spindle speed. The invention installs a marker with high contrast and periodic texture on the upper end of a yarn tube, and optimizes its geometric shape, material and installation angle, so that the image is stable and clear during high-speed rotation, the detection accuracy of weak twist phenomenon is improved, the exposure time and sampling rate are dynamically adjusted, and images can be stably captured at different rotation speeds, and the blur and noise problems in dynamic scenes in traditional methods are overcome. Dynamic features are effectively extracted by denoising, edge detection and rotation feature analysis of the collected image, and weak twist phenomenon is accurately judged by marker position matching and stability evaluation. In addition, based on the image analysis result, the textile detection strategy is adjusted in combination with the generated signal, and instant feedback and adjustment are provided, thereby improving the quality control efficiency and equipment response speed in the production process.
Description
Technical Field
The invention relates to the technical field of textile spindle speed detection, in particular to a method for dynamically detecting and extracting characteristics of a textile spindle.
Background
The spinning spindle speed is a dynamic parameter in the spinning process, so that the formation of yarn twist and the stability of quality are affected, the yarn is twisted by synchronous rotation of a spool and a spindle in the spinning process, a certain twist is formed, the yarn tension is directly affected by spindle speed change, and the strength and uniformity of the yarn are further affected, so that weak twist is caused;
The weak twisting is a common abnormal phenomenon in the spinning process, and refers to the problem that the rotation speed synchronism between a yarn tube and a spindle is insufficient, so that yarn twist is low, the yarn twist is a key factor influencing the quality of textiles, and the insufficient twist can cause uneven yarn tension, reduced yarn strength, loose textile structure and the like, thereby influencing the quality and market competitiveness of products.
The prior art has the defects that the spinning process is carried out under high-speed rotation, in the process of carrying out image acquisition on spinning, image blurring and data loss are easy to occur due to asynchronous acquisition of a stroboscope and the rotating speed of a yarn tube, the reliability of weak twist judgment is influenced, the traditional image processing and dynamic feature extraction precision is insufficient, the synchronism difference of the yarn tube and a spindle is difficult to effectively identify, excessive defective products are caused, and the benefit is influenced.
Disclosure of Invention
In order to overcome the defects in the prior art, the scheme is as follows, so as to solve the problem of poor detection precision of the spinning spindle speed in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
The method for dynamically detecting and extracting the characteristics of the textile ingot comprises the following steps:
A mark with high contrast and periodic texture is arranged at the upper end of the bobbin, and the geometric shape, the material and the installation angle of the mark are optimized;
Setting a camera and a stroboscope, dynamically adjusting exposure time and sampling rate, and collecting images at different rotating speeds;
Denoising, edge detection and rotation feature analysis are carried out on the acquired image, dynamic features are extracted through marker position matching and stability evaluation, and comprehensive evaluation is carried out on the quality of the markers to determine whether a weak twisting phenomenon occurs;
and acquiring and analyzing image extraction information generated in the process of evaluating the weak twist phenomenon, and carrying out textile detection strategy adjustment according to different signals generated by analysis.
In a preferred embodiment, a marker with high contrast and periodic texture is mounted on the upper end of the bobbin, and the marker geometry, material and mounting angle are optimized, specifically as follows:
Adding a cover-shaped mark at the upper end of the bobbin, designing the shape of the cover-shaped mark as a triangle or a two-dimensional code, adding periodic stripes or textures on the surface of the mark, and calculating the edge sharpness, the reflectivity and the coverage rate of the cover-shaped mark;
Dynamically shooting the mark by using a high-frame-rate camera and a stroboscope combination, recording the mark definition at different rotation speeds, and adjusting the flicker frequency of the stroboscope according to the dynamic ambiguity and the light reflection intensity of the mark;
And (3) evaluating the comprehensive quality of the mark by comprehensive edge sharpness, reflectivity, coverage rate and dynamic ambiguity, establishing a mark scoring model, and determining optimal mark parameters and a layout scheme.
In a preferred embodiment, a camera and a stroboscope are arranged, the exposure time and the sampling rate are dynamically adjusted, and the image acquisition is carried out at different rotation speeds, and the specific steps comprise:
Initializing frequency calculation and synchronization of a stroboscope, acquiring rotating speed data of a spool through a sensor, calculating the optimal flicker frequency of the stroboscope according to the rotating speed of the spool, setting up the flicker time of the stroboscope to be dynamically adjusted, and enabling the flicker interval of each time to be consistent with the rotation of a mark;
According to the frequency of the stroboscope, the sampling rate of the camera is set to be synchronous with the stroboscope, the exposure time and the aperture size of the camera are adjusted, and the jitter between frames is detected;
performing definition detection on the image acquired in real time, evaluating the edge ambiguity of the mark, and if the ambiguity exceeds the ambiguity threshold, adjusting the flicker frequency of the stroboscope or the sampling rate of the camera, and recalibrating for synchronization;
When the image edge ambiguity is greater than the image edge ambiguity threshold, increasing the stroboscope frequency or adjusting the exposure time;
when the image edge ambiguity is less than or equal to the image edge ambiguity threshold, then the current frequency and exposure setting remain unchanged.
In a preferred embodiment, denoising, edge detection and rotation feature analysis are performed on the acquired image, dynamic features are extracted through marker position matching and stability evaluation, and the quality of the markers is comprehensively evaluated to determine whether a weak twisting phenomenon occurs, which specifically comprises the following steps:
Denoising by using median filtering, and replacing each pixel value with a median in the neighborhood of the pixel;
Extracting mark edge information in the image through a Canny edge detection algorithm;
extracting dynamic behavior of the mark by analyzing the rotation characteristics of the mark in the image sequence, wherein the dynamic characteristic behavior of the mark comprises rotation speed and rotation angle change,
Calculating the rotation speed of the mark based on the time continuity of the image sequence, and judging the stability of the rotation state according to the rotation angle change rate;
The gradient information of the image edges is used to calculate the motion blur, a local mean shift algorithm is used to evaluate the blur of each frame of image and the motion blur value is compared with a threshold.
Analyzing the tracking stability of the mark through the mark position change between the continuous frame images;
And comprehensively evaluating the quality of the mark by combining the rotation speed, the ambiguity and the tracking stability of the mark to obtain a final mark quality score, and determining the weak twist phenomenon.
In a preferred embodiment, the quality of the mark is comprehensively evaluated to determine whether the weak twist phenomenon occurs, and the method comprises the following steps:
comparing the mark quality score with a weak twist threshold;
and if the mark quality score is smaller than the weak twist phenomenon threshold value, determining that the weak twist phenomenon occurs, and analyzing the mark.
In a preferred embodiment, the image extraction information generated by the evaluation of the weak twist phenomenon is obtained and analyzed, comprising the steps of:
Acquiring image extraction information generated in the process of evaluating the weak twist phenomenon, wherein the image extraction information comprises dynamic characteristic information and image scale information;
The dynamic characteristic information comprises a rotation dynamic characteristic index, and the image scale information comprises an image definition index;
the acquired rotation dynamic characteristic index and the image definition index are combined to generate a spinning judgment coefficient;
the rotation dynamic characteristic index and the image definition index are in direct proportion to the spinning judgment coefficient.
In a preferred embodiment, and according to the different signals generated by the analysis, the textile detection strategy adjustment is performed, comprising the following steps:
Comparing the generated prediction adjustment coefficient with a set textile state judgment threshold value;
if the prediction adjustment coefficient is greater than or equal to the weaving state judgment threshold value, generating a weaving detection stable signal, wherein the weaving process is normal without additional intervention;
If the predicted adjustment coefficient is smaller than the weaving state judgment threshold value, generating a weaving detection state abnormal signal to remind a producer or a system operator of taking measures to perform weaving intervention.
The method for dynamically detecting and extracting the characteristics of the textile spindle has the technical effects and advantages that:
The invention realizes the high-efficiency detection of the weak twisting phenomenon in the spinning process by installing the mark with high contrast and periodical textures at the upper end of the bobbin and combining an accurate image acquisition and processing method, ensures that the mark has a stable and clear image in the high-speed rotation process by optimizing the geometric shape, the material and the installation angle of the mark, improves the detection precision, the camera and the stroboscope work cooperatively, dynamically adjusts the exposure time and the sampling rate, can stably capture images at different rotating speeds, overcomes the problems of blurring and noise which are easy to occur in a dynamic scene in the traditional method, carries out denoising treatment, edge detection and rotation characteristic analysis on the acquired images, can effectively extract dynamic characteristics, accurately judges whether the weak twisting phenomenon exists or not by carrying out position matching and stability evaluation on the mark, and in addition, adjusts the spinning detection strategy by combining generated signals based on the analysis of image extraction information, thereby realizing the instant feedback and adjustment of the pertinence problem, improving the quality control efficiency in the production process, and greatly improving the detection precision and response speed of spinning equipment.
Drawings
FIG. 1 is a schematic flow chart of the method for dynamically detecting and extracting characteristics of a textile spindle.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to achieve the above purpose, fig. 1 shows a schematic structure diagram of the method for detecting the dynamic state and extracting the characteristics of the spinning spindle according to the present invention, which comprises the following steps;
A mark with high contrast and periodic texture is arranged at the upper end of the bobbin, and the geometric shape, the material and the installation angle of the mark are optimized;
Setting a camera and a stroboscope, dynamically adjusting exposure time and sampling rate, and collecting images at different rotating speeds;
Denoising, edge detection and rotation feature analysis are carried out on the acquired image, dynamic features are extracted through marker position matching and stability evaluation, and comprehensive evaluation is carried out on the quality of the markers to determine whether a weak twisting phenomenon occurs;
and acquiring and analyzing image extraction information generated in the process of evaluating the weak twist phenomenon, and carrying out textile detection strategy adjustment according to different signals generated by analysis.
Step 1, performing textile marking design and installation optimization, adding a cover-shaped mark at the upper end of a yarn tube, combining a combined photographing system of a camera and a stroboscope, optimizing marking design and installation layout, and ensuring the identification precision of the mark in dynamic detection of a textile spindle, wherein the method comprises the following specific steps:
The upper end of the bobbin is added with a cover-shaped mark, the shape of the mark is designed into an asymmetric geometric pattern (such as a triangle or a two-dimensional code) with high contrast, and periodic stripes or textures are added on the surface of the mark, so that stable dynamic characteristics are generated when the mark rotates, the camera is convenient to capture, and the sharpness of the edge is marked, wherein the formula is as follows: Wherein, the method comprises the steps of, wherein, For the brightness distribution of the marks,AndFor an edge interval, the edge sharpness is the rate of change of the edge gradient in unit radian:
marking with a material having high reflectivity (such as coated plastic or reflective coating) to reduce interference from ambient light variations, and coating the surface of the marking with a fluorescent coating to improve identification in dark environments, the reflectivity of the marking being defined as the intensity of the reflected light of the marking With incident light intensityRatio of (3): Reflectance of light Directly influencing the visibility of the mark in a light complex environment;
the method comprises the steps of arranging and installing marks, symmetrically arranging a plurality of marks at the upper end of a spool, ensuring that at least one mark is positioned in a view field of a camera under any rotation angle, adjusting the included angle between the mark and the surface of the spool, keeping stable optical characteristics in the rotation process, reducing visual distortion caused by rotation, carrying out mathematical modeling on the arrangement position of each mark, and optimizing the coverage rate of mark layout;
The coverage rate C is defined as the probability in the field of view of the camera, and the calculation formula is as follows: Wherein, the method comprises the steps of, wherein, Covering angles for the field of view of the ith mark, n being the number of marks;
The method has the advantages that the mark is dynamically shot by using the combination of the high-frame-rate camera and the stroboscope, so that the dynamic characteristics of the mark are clearly visible in rotation, namely, the mark definition under different rotation speeds is tested, key indexes such as mark ambiguity, light reflection intensity and the like are analyzed, the flicker frequency of the stroboscope is optimized, the flicker frequency is consistent with the rotation speed of the bobbin, and the motion ambiguity and the dynamic ambiguity are reduced Is the change rate of the boundary displacement, and the formula is: Wherein, the method comprises the steps of, wherein, In order to mark the boundary displacement function,The boundary position is marked statically, and T is the sampling time;
Dynamically adjusting geometric shapes or material parameters of marks with poor performance (such as low recognition rate or insufficient reflectivity) in the test, and performing iterative optimization on the arrangement positions and the number of the marks according to a data analysis result so that the recognition rate of the marks in a camera and stroboscope combined shooting system reaches a target value (such as more than or equal to 95 percent);
And (3) comprehensively estimating parameters such as edge sharpness, reflectivity, coverage rate, dynamic ambiguity and the like, evaluating the comprehensive quality of the mark, establishing a mark scoring model, outputting optimal mark parameters and a layout scheme to a subsequent image processing step, wherein the comprehensive scoring model is as follows: Wherein, the method comprises the steps of, wherein, 、、、And the weight coefficient is adjusted according to actual requirements.
Step 2, synchronously controlling the image acquisition and the stroboscope, after the mark design and the installation optimization are finished, ensuring the definition and the stability of the image acquisition through the synchronous control of the high-frame-rate camera and the stroboscope, and providing high-quality original data for subsequent image processing and dynamic feature extraction, wherein the method comprises the following specific steps of:
initializing frequency calculation and synchronization of the stroboscope to obtain rotating speed data of the bobbin (In units of revolutions per second), provided by a sensor or an initial set point, the optimum flicker frequency of the stroboscope is calculated from the rotational speed of the bobbinTo match the dynamic period of the mark and set the flash time of the dynamic adjustment stroboscopeEnsuring that each scintillation interval is consistent with the rotation of the mark, the formula is: flicker frequency of stroboscope And time intervalIs used for strobe control for frequency adjustment;
Setting the sampling rate of the camera according to the frequency of the stroboscope Ensures synchronization with the stroboscope, and can dynamically adjust the exposure time of the cameraAnd aperture size, optimizing image acquisition quality under light conditions, the formula is: wherein k is a sampling redundancy coefficient;
The exposure time formula is: Wherein, the method comprises the steps of, wherein, For a desired light intensity,For the intensity of the ambient light,The exposure correction coefficient;
The exposure time is directly related to the stroboscopic interval, the stability and moderate brightness of the mark acquired by each frame are ensured, a sampling redundancy coefficient is added in the calculation of the sampling rate, the complete record of the mark is ensured, and even if slight rotation speed fluctuation occurs, the frame is not lost;
The method comprises the steps of detecting the definition of an image acquired in real time, evaluating the edge ambiguity of a mark, and if the ambiguity exceeds an ambiguity threshold value, adjusting the flicker frequency of a stroboscope or the sampling rate of a camera, and recalibrating and synchronizing, wherein the formula is as follows: Wherein, the method comprises the steps of, wherein, In order to provide an image edge degree of blurring,At pixel point for imageN is the total number of pixels in the image;
When (when) (Image edge ambiguity is greater than the image edge ambiguity threshold), increasing the stroboscopic frequency or adjusting the exposure time;
When (when) (Image edge ambiguity is less than or equal to the image edge ambiguity threshold), the current frequency and exposure setting remain unchanged;
the brightness gradient change in the ambiguity detection formula reflects the sharpness of the edge in the image, and the clear mark edge is helpful for improving the recognition rate;
when the bobbin rotates at a high speed, the marked images may generate inter-frame jitter due to equipment vibration or synchronization errors, which may cause instability of marked positions in continuous images, dynamic deviation in an image sequence is eliminated through inter-frame analysis and jitter correction algorithm, data consistency is ensured, namely, the position stability of the marks is analyzed through multi-frame images acquired in real time, inter-frame jitter is detected, and the jitter is corrected through an image registration algorithm (such as an optical flow method), so that consistency of the image sequence is ensured: Wherein, the method comprises the steps of, wherein, In order to mark the position stability,For marking the position coordinates at time t, whenAt this time, inter-frame jitter correction is started,Is a marker position stability threshold;
In the formula of the position stability of the mark, the position change rate reflects the dynamic stability of the mark on a time axis, and a stable image sequence is critical to the subsequent weak twist detection and dynamic characteristic analysis;
The step solves the problems of image blurring and position deviation of the dynamic marking of the yarn tube under high-speed rotation by the technical means of synchronous control, definition detection, shake correction and the like of the stroboscope and the camera, and finally outputs high-quality image sequences and accurate acquisition parameters.
Step 3, carrying out dynamic feature extraction and mark recognition, and carrying out dynamic feature extraction and mark recognition on the acquired image sequence after image acquisition and synchronous control are completed, wherein the specific steps are as follows:
In the image sequence, due to possible environmental noise or sensor errors, denoising is needed, and a Gaussian filter method or a median filter method and the like can be used for eliminating noise points in the image, so that the precision of subsequent feature extraction is ensured, and the specific processing steps are as follows:
Denoising by using median filtering, and replacing each pixel value with a median in the neighborhood of the pixel;
the edge detection algorithm, such as Canny edge detection, extracts the mark edge information in the image, further improves the identifiability of the image, and the edge detection is helpful for determining the accurate position and outline of the mark, and the Canny edge detection algorithm has the following formula: Wherein, the method comprises the steps of, wherein, To be in the imageA luminance function of the location and,Is the second partial derivative of the image;
by analyzing the rotation characteristics of the marks in the image sequence, extracting dynamic behavior of the marks, such as rotation speed, rotation angle variation, etc., the rotation speed of the marks can be calculated based on the time continuity of the image sequence And judging the stability of the rotation state according to the change rate of the rotation angle, wherein the formula is as follows: Wherein, the method comprises the steps of, wherein, For time intervals ofThe angular variation of the rotation of the inner mark;
In general, in image processing, an image brightness function represents a brightness (or intensity) value of each pixel in an image, where the brightness value is usually a gray scale value and reflects a brightness degree of a certain pixel point, and in a color image, brightness values of three channels of red, green and blue may be represented respectively, and in textile detection, the image brightness function reflects light intensity information of each pixel in the image and is used for capturing characteristics of a textile mark. If the image definition is high, the brightness function can provide a clear and contrast-intensive marked image;
The evaluation of the dynamic ambiguity is used for judging whether the mark has excessive ambiguity in the high-speed rotation process, the ambiguity is evaluated by using gradient information of the image edge according to the definition in the step 1, the ambiguity of each frame of image can be evaluated by using a local mean shift (LMD) algorithm, and the ambiguity value is compared with a threshold value, and the formula of the dynamic ambiguity is as follows: Wherein, the method comprises the steps of, wherein, As a function of the dynamic displacement of the marks,Is a static position;
The dynamic displacement function is the displacement of the mark in the rotary system at a certain point in time t, in particular the mark may be a small physical mark or feature point, the position of which changes with rotation or other dynamic changes during the textile production process, and the dynamic displacement of the mark is a mathematical function describing the motion trail of the mark with time. It may reflect the rotational dynamics of the bobbin, the speed of variation, or displacement anomalies due to process problems (such as a weak twist phenomenon), for example, if the mark is a small object placed on the bobbin, the dynamic displacement function may represent the variation of the displacement of the mark in a certain direction (such as axial or radial) during rotation, which function helps to analyze the stationarity and irregularities of the rotation process;
Performing feature matching on the marks in each frame of image, and comparing the marks with a preset mark template by adopting a template matching technology to extract the position information of the marks, wherein a template matching formula is as follows: Wherein, the method comprises the steps of, wherein, For the image to be identified,In the case of a template image,In order for the degree of matching to be achieved,
The tracking stability of the mark is analyzed through the mark position change between continuous frame images, the position consistency of the mark in an image sequence is ensured, the mark position is estimated in real time, and the formula of an optical flow method is as follows: where v is the motion vector of the pixel, Is the gradient of the image;
The quality of the mark is comprehensively evaluated by combining a plurality of dynamic characteristics such as the rotation speed, the ambiguity, the tracking stability and the like of the mark, the scores of the characteristics are combined by a weighted fusion method to obtain a final mark quality score, and the final mark quality score can be fused by adopting a weighted average method or a more complex fuzzy logic method, and the method comprises the following concrete steps:
The marking quality scoring formula is: Wherein, For the marker to track the stability score,The weight coefficient of each feature;
according to the dynamic characteristics extracted in the step 3, analyzing whether the dynamic behavior of the mark meets the standard of the weak twist phenomenon, for example, the mark has slower and stable rotating speed, higher ambiguity, unstable rotating angle change and the like, which can be regarded as the indication of the weak twist phenomenon;
The criterion for the occurrence of the weak twist phenomenon may be defined as: Wherein, the method comprises the steps of, wherein, A preset weak twist threshold;
After the dynamic feature extraction and mark recognition stage is completed, after partial weak twisting phenomenon is determined to occur, comprehensive analysis is required to be carried out on multi-dimensional features such as rotation features (rotation speed), ambiguity, tracking stability and the like of the mark, so that whether the weak twisting phenomenon exists actually and subsequently is judged, and corresponding alarm or adjustment operation is triggered according to a judging result;
If the weak twist phenomenon is limited to only very small parts of the textile and these parts do not significantly affect the final quality of the textile during the overall production process, such phenomena may be negligible, especially in mass production, local irregularities may not affect the functionality or appearance of the final product, if the weak twist phenomenon occurs over a plurality of parts or a sustained period of time and the quality problems of these parts may significantly affect the strength, softness or other functional indicators of the final product, they should not be ignored, even if these phenomena appear to be very small at an early stage, so that further detection determinations are required;
Comprehensively evaluating the weak twist phenomenon by using the extracted features (such as rotation speed, ambiguity, tracking stability and the like), evaluating and analyzing each dynamic feature, and acquiring image extraction information generated in the process of evaluating the weak twist phenomenon, wherein the image extraction information comprises dynamic feature information and image scale information;
the dynamic characteristic information comprises a rotation dynamic characteristic index and is marked as XZD, and the image scale information comprises an image definition index and is marked as QXD;
The rotation dynamic characteristic index is used for measuring dynamic behavior characteristics of the yarn tube in the rotation process, particularly the change and stability of the rotation speed and nonlinear dynamic phenomena (such as oscillation, abrupt acceleration or deceleration and the like) possibly occurring in the rotation process, and combines the time domain characteristics and the frequency domain characteristics in the rotation process so as to comprehensively capture the tiny change and the complex dynamics of the rotation process, particularly the behavior pattern related to the weak twisting phenomenon;
The stability of the rotation process is reflected by monitoring the rotation rate variation, in particular frequent fluctuations or abnormal speed variations, which may indicate an abnormal phenomenon in the rotation process, such as a weak twist, if the rotation rate variation is severe or irregular:
In the evaluation process of the weak twisting phenomenon, the rotating dynamic characteristic index serves as a dynamic behavior monitoring tool, potential abnormal changes in the rotating process of the yarn tube can be revealed, the weak twisting phenomenon is usually represented as abrupt changes or unstable behaviors of the rotating speed of the yarn tube, and the phenomena can be quantified and detected through the rotating dynamic characteristic index;
The weak twisting phenomenon is usually accompanied by unstable rotation of the yarn tube, such as sudden increase or sudden decrease of the rotation rate, or frequent fluctuation of the rotation rate, and the abnormal dynamics can be captured by time-frequency analysis and nonlinear dynamics characteristics of the rotation dynamic characteristic index, so that the weak twisting phenomenon can be found in advance;
The acquisition logic of the rotation dynamic characteristic index is as follows:
Rotational speed data XZ (t) is acquired by a rotational sensor and the data is sliced into time windows And carrying out short-time Fourier transform on the acquired rotation speed signal, extracting the frequency domain characteristics of the rotation signal, wherein the formula is as follows: In which, in the process, Is a window function, for defining the signal content around time t,Is a complex exponential function, representing the frequency content,Is a time variable representing the instantaneous value of the signal, f is a frequency variable representing the frequency in the frequency domain;
For rotational speed data And calculating Lyapunov indexes, wherein the formula is as follows: the rotation dynamic characteristic index is calculated based on the frequency domain characteristic of STFT and Lyapunov index, and the formula is as follows: ;
It should be noted that, the Lyapunov index is used to measure the sensitivity and chaos characteristics of the rotation speed, and the index describes the stability of the speed change, and the larger the Lyapunov index, the more unstable the system, and the possibility of weak twisting.
The image sharpness index (QXD) is used to measure the sharpness, sharpness and visibility of a target object (in this case a mark on a bobbin) in an image. It evaluates the overall quality and detail performance of an image by analyzing edge sharpness, contrast, noise level, and texture features in the image. The higher definition image means that the edges of the mark are sharper, have stronger contrast and are less susceptible to noise interference;
The sharpness of an image is closely related to the sharpness of edges. A sharp image will exhibit sharp edges, while a blurred image will obscure the edges and blur the transition. Sharpness is usually quantified by edge gradients, second derivatives, etc., with sharp labels meaning that edges change faster and can be accurately identified;
The image definition index serves as a key visual quality detection tool in the evaluation process of the weak twisting phenomenon, so that the evaluation of whether the dynamic characteristics of the bobbin mark can be clearly captured is facilitated, the accuracy and judgment of the weak twisting phenomenon are crucial, the weak twisting phenomenon is usually accompanied with instability of the bobbin rotation, the fluctuation of the rotation rate can directly influence the definition of an image, especially, the image blurring or distortion phenomenon can occur when the bobbin rotates at a high speed, the image definition index ensures that the image is clear enough to capture the tiny change of the mark when the dynamic characteristics are extracted by monitoring the image quality in real time;
The marks may be blurred dynamically during high rotation, especially when a weak twist occurs, and the rotation of the marks may be unstable, causing blurring or distortion of the marks in the image. The image definition index can help to detect the fuzzy areas in real time, guide the system to adjust shooting parameters (such as exposure time, aperture and the like), optimize image quality, ensure that marks are always clear, and further evaluate the weak twist phenomenon more accurately;
the image sharpness index acquisition logic is as follows:
Wavelet transformation is carried out on the marked image captured by the camera, and image features under different frequencies are extracted in a multi-scale mode;
The edge information of the image is extracted by Canny edge detection, focusing particularly on the sharpness of the marker edges. Image sharpness is evaluated by using edge intensity and distribution characteristics, expressed as: Wherein, the method comprises the steps of, wherein, For the wavelet transform coefficients,Is a wavelet basis function;
obtaining the image definition of the edge information of the image, and calculating an image gradient value calculation expression as follows: In which, in the process, A gradient of the brightness is indicated,AndThe method respectively represents the change rates of the image in the horizontal direction and the vertical direction, calculates the nonlinear ambiguity value of the image by using the high-step ambiguity measure, and the calculation expression is as follows: In which, in the process, 、Respectively representing the positions of the ith pixel in the horizontal direction and the vertical direction, wherein N is the total number of pixels;
Calculating an image definition index, wherein the calculation expression is as follows: 。
it should be noted that the wavelet transform can capture local details, textures and edge information in the image, and the high-step ambiguity measure is used for introducing the nonlinear ambiguity degree of the image, and the higher-step ambiguity information in the image is captured by the ambiguity measure through the second derivative, the stronger the edge blur, the worse the image quality.
Generating a spinning judgment coefficient by combining dynamic characteristic information and image scale information, namely, generating a spinning judgment coefficient by combining acquired rotation dynamic characteristic indexes and image definition indexesThe expression is: In which, in the process, 、A preset proportionality coefficient for rotating dynamic characteristic index and image definition index, and、Are all greater than 0.
The specific method for generating the textile decision coefficient in a simultaneous manner may involve various algorithms and models, depending on the actual situation and the application requirements, and the embodiment may use a weighted summation manner to combine the rotation dynamic characteristic index and the image sharpness index to generate a comprehensive textile decision coefficient, where the comprehensive textile decision coefficient may be used as an input for comprehensively evaluating the weak twist phenomenon to determine the final weak twist phenomenon.
It should be noted that, the size of the preset scaling factor is a specific numerical value obtained by quantizing each parameter, which is used for facilitating the subsequent comparison, and regarding the size of the factor, depends on how many sample data and how many sample data are and the preset scaling factors that are initially set by a person skilled in the art for each group of sample data, and is not unique, as long as the proportional relationship between the parameter and the quantized numerical value is not affected, if the rotational dynamic characteristic index and the textile decision coefficient are in a proportional relationship, the rotational dynamic characteristic index and the image definition index are normalized to have the same dimension and range, which can be achieved by subtracting the average value from the original data and dividing the average value by the standard deviation, or mapping the data to the range of [0,1 ].
The larger the rotation dynamic characteristic index is, the larger the image definition index is, the larger the spinning judgment coefficient generated by the combination is, which indicates that the bobbin has better rotation stability when rotating at high speed, the marked dynamic characteristic change rule is clear, no obvious abnormal fluctuation or instability exists, the rotation process of the textile is stable, the image acquisition quality is good, the detail information of the textile can be accurately acquired in the detection process, thus obtaining accurate quality assessment, which generally indicates that the quality of the textile is higher and accords with the production standard;
The smaller the rotation dynamic characteristic index and the smaller the image definition index, the smaller the spinning judgment coefficient generated simultaneously, which indicates that unstable factors possibly exist in the rotating process of the yarn tube, such as larger fluctuation of the rotating speed and irregular change of the dynamic characteristic of the mark, so that the mark in the image is blurred or distorted. This indicates that the rotational stability of the tube is poor and that there may be process or equipment problems, resulting in an inability to effectively identify dynamic characteristics or quality problems of the textile. This generally means that textiles have quality problems such as insufficient strength, appearance defects, irregular textiles, etc.;
comparing the generated weaving judgment coefficient with a preset weaving state judgment threshold value to generate a weaving detection stable signal and a weaving detection state abnormal signal;
after the weaving judgment coefficient is obtained, comparing the weaving judgment coefficient with a weaving state judgment threshold value;
if the textile judgment coefficient is greater than or equal to the textile state judgment threshold, a textile detection stable signal is generated at the moment, so that the textile performance accords with the expectations in terms of rotation dynamic characteristics and image definition, the dynamic characteristics marked in the rotation process are clear and stable, the image acquisition quality is higher, the detection can accurately identify the state and quality of the textile, the textile detection can normally operate in the working process, the equipment does not have faults or unstable phenomena, the acquired image information is reliable, the textile production line does not have obvious quality problems in the manufacturing process, and the product is in a good state without additional intervention;
If the textile determination coefficient is smaller than the textile state determination threshold, generating a textile detection state abnormal signal, wherein the abnormal signal indicates that the equipment may have faults or instability, for example, the rotating system is unstable, the image acquisition equipment has problems (such as insufficient light source, inaccurate focusing, vibration interference and the like), the image quality is poor, the dynamic characteristics of the textile cannot be accurately acquired, and the generation of the abnormal signal reminds production personnel or system operators that measures need to be taken for intervention and repair, wherein the specific measures include:
Checking and adjusting equipment, namely checking whether the rotating equipment, the image acquisition equipment, the stroboscope and the like have faults or unstable operation, and carrying out necessary repair or adjustment:
optimizing production parameters, namely if the process problem is judged, adjusting the production parameters such as rotation speed, tension and the like to ensure the stability of the bobbin rotation process;
The image acquisition quality is enhanced, namely, the settings of the light source, exposure, focusing and the like are checked, the image acquisition process is ensured not to be disturbed, and the image definition is improved.
Material and process adjustments if problems occur in the textile itself (e.g., weak twist or uneven quality), attempts may be made to adjust the textile parameters of the raw materials, optimize the textile process, and avoid similar problems from reoccurring.
In summary, the textile detection stable signal indicates that the quality of the current textile meets the standard, the equipment and the process are stable, the production and detection system is in a good working state, normal production and detection operation can be continued, the textile detection state abnormal signal indicates that the textile has quality problems or abnormal production process, and corresponding intervention measures such as checking equipment, adjusting production parameters, optimizing image acquisition, improving material process and the like are needed to be adopted so as to recover the normal operation of the production line and improve the product quality;
It should be noted that, in this embodiment, the relevant threshold information is preset by a professional, and is not explained here too much, and some of the parameters in the embodiment have the same english letters, but are explained in different meanings when in use, and are not explained here one by one.
The invention realizes the high-efficiency detection of the weak twisting phenomenon in the spinning process by installing the mark with high contrast and periodical textures at the upper end of the bobbin and combining an accurate image acquisition and processing method, ensures that the mark has a stable and clear image in the high-speed rotation process by optimizing the geometric shape, the material and the installation angle of the mark, improves the detection precision, the camera and the stroboscope work cooperatively, dynamically adjusts the exposure time and the sampling rate, can stably capture images at different rotating speeds, overcomes the problems of blurring and noise which are easy to occur in a dynamic scene in the traditional method, carries out denoising treatment, edge detection and rotation characteristic analysis on the acquired images, can effectively extract dynamic characteristics, accurately judges whether the weak twisting phenomenon exists or not by carrying out position matching and stability evaluation on the mark, and in addition, adjusts the spinning detection strategy by combining generated signals based on the analysis of image extraction information, thereby realizing the instant feedback and adjustment of the pertinence problem, improving the quality control efficiency in the production process, and greatly improving the detection precision and response speed of spinning equipment.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product.
Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally, the foregoing description of the preferred embodiment of the invention is provided for the purpose of illustration only, and is not intended to limit the invention to the particular form disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411848115.6A CN119313660A (en) | 2024-12-16 | 2024-12-16 | Dynamic detection and feature extraction method of textile spindle speed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411848115.6A CN119313660A (en) | 2024-12-16 | 2024-12-16 | Dynamic detection and feature extraction method of textile spindle speed |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119313660A true CN119313660A (en) | 2025-01-14 |
Family
ID=94184848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411848115.6A Pending CN119313660A (en) | 2024-12-16 | 2024-12-16 | Dynamic detection and feature extraction method of textile spindle speed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119313660A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB791477A (en) * | 1955-04-23 | 1958-03-05 | British Rayon Res Ass | Improvements in or relating to the measurement of the lustre of textile fabrics |
| CN106087154A (en) * | 2016-08-24 | 2016-11-09 | 宁夏如意科技时尚产业有限公司 | A kind of problem spindle alignment system for spinning frame and method |
| CN114264661A (en) * | 2021-12-06 | 2022-04-01 | 浙江大学台州研究院 | A method, device and system for web detection with self-adaptive definition |
| CN118127683A (en) * | 2024-03-06 | 2024-06-04 | 上海致景信息科技有限公司 | Spindle speed measuring method based on vision, computer and measuring robot |
| CN118351100A (en) * | 2024-04-30 | 2024-07-16 | 武汉兰丁智能医学股份有限公司 | Image definition detection and processing method based on deep learning and gradient analysis |
| CN118429242A (en) * | 2024-04-29 | 2024-08-02 | 河北农业大学 | Image analysis method and system based on deep learning |
| CN118941553A (en) * | 2024-09-12 | 2024-11-12 | 曲阜金絮龙纺织有限公司 | A Yarn Detection System Based on Image Processing |
-
2024
- 2024-12-16 CN CN202411848115.6A patent/CN119313660A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB791477A (en) * | 1955-04-23 | 1958-03-05 | British Rayon Res Ass | Improvements in or relating to the measurement of the lustre of textile fabrics |
| CN106087154A (en) * | 2016-08-24 | 2016-11-09 | 宁夏如意科技时尚产业有限公司 | A kind of problem spindle alignment system for spinning frame and method |
| CN114264661A (en) * | 2021-12-06 | 2022-04-01 | 浙江大学台州研究院 | A method, device and system for web detection with self-adaptive definition |
| CN118127683A (en) * | 2024-03-06 | 2024-06-04 | 上海致景信息科技有限公司 | Spindle speed measuring method based on vision, computer and measuring robot |
| CN118429242A (en) * | 2024-04-29 | 2024-08-02 | 河北农业大学 | Image analysis method and system based on deep learning |
| CN118351100A (en) * | 2024-04-30 | 2024-07-16 | 武汉兰丁智能医学股份有限公司 | Image definition detection and processing method based on deep learning and gradient analysis |
| CN118941553A (en) * | 2024-09-12 | 2024-11-12 | 曲阜金絮龙纺织有限公司 | A Yarn Detection System Based on Image Processing |
Non-Patent Citations (2)
| Title |
|---|
| 计万平 等: "浅谈细纱锭子运行状态对纱线捻度不匀的影响", 《纺织器材》, no. 01, 30 January 2018 (2018-01-30) * |
| 赵龙飞 等: "面向智能纺纱构建的单锭监测系统及其应用", 《现代纺织技术》, 23 September 2024 (2024-09-23) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116758491B (en) | Printing monitoring image analysis method and system applied to 3D printing | |
| EP3677922B1 (en) | Image-based inspection for physical degradation of an air data probe | |
| CN116612112B (en) | Visual inspection method for surface defects of bucket | |
| CN114140384A (en) | Transverse vibration image recognition algorithm for hoisting steel wire rope based on contour fitting and centroid tracking | |
| CN116721096B (en) | New energy harness quality online detection method based on artificial intelligence | |
| CN117455870A (en) | Connecting wire and connector quality visual detection method | |
| CN115330799B (en) | Automatic fault diagnosis method for instrument | |
| CN117314826A (en) | Performance detection method of display screen | |
| CN119147540B (en) | Yarn quality detection system, method and device | |
| CN119313660A (en) | Dynamic detection and feature extraction method of textile spindle speed | |
| CN117928401B (en) | Polymer monofilament wire diameter detection device and detection method based on machine vision | |
| CN117392127B (en) | Method and device for detecting display panel frame and electronic equipment | |
| US20200408697A1 (en) | Belt inspection system, belt inspection method, and recording medium for belt inspection program | |
| CN118379230A (en) | Image quality optimization system of automobile DMS camera | |
| CN112488986A (en) | Cloth surface flaw identification method, device and system based on Yolo convolutional neural network | |
| US20210374942A1 (en) | Belt examination system and computer-readable non-transitory recording medium having stored belt examination program | |
| CN115708133A (en) | System, method and device for reading a measuring device, storage medium | |
| CN119147539B (en) | Ribbon quality inspection system and method based on industrial camera inspection | |
| CN119152525B (en) | A transparent bottle curved surface printed graphics and text detection system based on AI vision | |
| CN119251220B (en) | Spacer vibration test result detection method based on machine vision | |
| CN118470766B (en) | A method for evaluating the wrinkle improvement effect of cosmetics | |
| CN118438080B (en) | Weld quality detection system and method based on welding data | |
| CN119399199A (en) | YOLOv 8-based tobacco leaf loose handling degree detection method and system | |
| CN119555697A (en) | Copper foil surface defect detection method, device, computer equipment and storage medium | |
| Wankhede et al. | Automatic edge detection of screen printed elliptical grids captured by modified USB microscope for single point strain analysis |
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 |