Textile yarn detection system and method based on linear array photoelectric sensor

Abstract

The invention provides a textile yarn detection system and method based on a linear array photoelectric sensor, and belongs to the technical field of textile production monitoring, and the system comprises a light source module which is arranged at one side of a detection area; the linear array sensing module is arranged on the other side, opposite to the light source module, of the detection area and used for generating corresponding linear array voltage signals according to the light intensity change received by each pixel receiving tube when the yarn penetrates through the detection area; and the data processing module is used for generating linear image data according to the received linear array voltage signal and processing the linear image data so as to detect the state of the yarn. The device has the advantages that high-precision detection of the yarn state is achieved, the breakage and pilling states and tension changes of the yarn can be monitored at the same time, and the quality control level and the production efficiency of textile production are remarkably improved; meanwhile, in combination with an image processing technology, normal yarn movement and yarn breakage conditions can be more effectively distinguished, false alarm and missing alarm are reduced, and the stability and reliability of detection are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of textile production monitoring, and particularly to a textile yarn detection system and method based on a linear array optoelectronic sensor. Background Art

[0002] In the textile industry, the stability of yarn quality directly determines the performance and appearance quality of the final fabric, and is a key link that cannot be ignored in the textile production process. For a long time, the textile industry has mainly used mechanical or manual methods to detect yarn quality. However, mechanical detection often has low detection accuracy due to the wear of mechanical components and accuracy limitations, and it is difficult to achieve real-time feedback. Manual detection, on the other hand, has problems such as strong subjectivity, low efficiency, high cost, and difficulty in coping with large-scale production.

[0003] With the rapid development of electronic technology and image processing technology, detection methods based on optoelectronic sensors have gradually emerged, bringing new possibilities for yarn quality detection in the textile field. For example, on textile machinery, the cutting frequency of the detection beam by the yarn during rapid movement is detected by an infrared optoelectronic sensor to determine whether the yarn is broken. Specifically, the high-frequency cutting of the detection beam by the yarn will generate a pulse signal with a certain frequency. When the frequency of the pulse signal is lower than a certain value or completely disappears, it is considered that the yarn has stopped moving or is out of the measurement range (broken wire or fracture).

[0004] However, when facing yarns with ultra-low speed intermittent movement, such as in the production process of fancy yarns, this infrared optoelectronic sensor is prone to false alarms of broken yarns due to the extremely low movement speed or intermittent stop of the yarn, resulting in unnecessary shutdowns and seriously affecting production efficiency.

[0005] In addition, pilling detection and tension monitoring of yarns are also crucial links in textile production. Pilling not only affects the aesthetics of the fabric but also may reduce its durability; while tension changes are directly related to the structural stability and uniformity of the fabric. However, existing optoelectronic sensors are mainly designed to detect yarn breakage and cannot be directly applied to pilling and tension monitoring. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a textile yarn detection system based on a linear array optoelectronic sensor; on the other hand, it also provides a textile yarn detection method based on a linear array optoelectronic sensor.

[0007] The technical problems solved by the present invention can be realized by the following technical solutions:

[0008] The first aspect of the present invention is to provide a textile yarn detection system based on a linear array optoelectronic sensor, including:

[0009] A light source module, which is arranged on one side of the detection area and is used to emit light towards the detection area;

[0010] A linear array sensing module, which is arranged on the other side of the detection area opposite to the light source module and is used to generate corresponding linear array voltage signals according to the light intensity changes received by each pixel receiving tube when the yarn passes through the detection area;

[0011] A data processing module, which is respectively connected to the light source module and the linear array sensing module, and is used to generate linear image data according to the received linear array voltage signals and process the linear image data to detect the state of the yarn.

[0012] Preferably, the linear array sensing module includes a complementary metal oxide semiconductor linear array sensor or a charge coupled device image sensor.

[0013] Preferably, the data processing module includes:

[0014] A calculation unit, which is used to calculate the difference between the maximum voltage and the minimum voltage in the linear array voltage signal;

[0015] A judgment unit, which is connected to the calculation unit and is used to judge whether the difference exceeds a preset threshold, and when the difference exceeds the preset threshold, it is determined that the yarn exists; and when the difference does not exceed the preset threshold, it is determined that the yarn is broken.

[0016] Preferably, the data processing module further includes:

[0017] A signal processing unit, which is used to perform zero-point removal processing on the linear array voltage signal to obtain a first signal;

[0018] An imaging unit, which is connected to the signal processing unit and is used to perform imaging processing according to the first signal to generate the linear image data.

[0019] Preferably, the signal processing unit is used to calculate the difference between the linear array voltage signal and a reference signal to obtain the first signal, and the reference signal is the signal output by each pixel of the linear array sensing module under the condition of no light source.

[0020] Preferably, the data processing module further includes:

[0021] An image preprocessing unit, which preprocesses the linear image data to obtain preprocessed linear image data;

[0022] A feature extraction unit, which is connected to the image preprocessing unit and is used to extract features from the preprocessed linear image data to obtain feature information;

[0023] An analysis unit, connected to the feature extraction unit, is configured to analyze based on the feature information to determine the yarn state.

[0024] Preferably, a pilling monitoring model is preset in the analysis unit, and the pilling monitoring model is used to determine a pilling monitoring result based on the feature information. The pilling monitoring result at least includes the pilling area, the type of each pilling area, and the size distribution of the pilling.

[0025] Preferably, a tension monitoring model is preset in the analysis unit, and the tension monitoring model is used to determine the tension change amount based on the feature information.

[0026] Preferably, the data processing module is further configured to generate real-time feedback information based on the yarn state and generate corresponding alarm information when the yarn state is abnormal.

[0027] A second aspect of the present invention is to provide a method for detecting textile yarns based on a linear array optoelectronic sensor, which is applied to the textile yarn detection system based on a linear array optoelectronic sensor as described above. The method includes:

[0028] The light source module emits light towards the detection area;

[0029] When the yarn passes through the detection area, the linear array sensing module generates corresponding linear array voltage signals according to the light intensity changes received by each pixel receiving tube;

[0030] Generate linear image data based on the received linear array voltage signals and process the linear image data to detect the yarn state.

[0031] The advantages or beneficial effects of the technical solution of the present invention are as follows:

[0032] By integrating the light source module, the linear array sensing module, and the data processing module, the present invention realizes high-precision detection of the yarn state, can simultaneously monitor the breakage, pilling state, and tension change of the yarn, significantly improves the quality control level and production efficiency of textile production; at the same time, combined with image processing technology, it can more effectively distinguish normal yarn movement from wire breakage, reduce false alarms and missed alarms, and further improve the stability and reliability of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic structural diagram of a textile yarn detection system based on a linear array optoelectronic sensor in a preferred embodiment of the present invention;

[0034] Figure 2 It is a schematic diagram of the voltage distribution on each pixel receiving tube when there is a yarn in a preferred embodiment of the present invention;

[0035] Figure 3In a preferred embodiment of the present invention, it is a schematic diagram of the optical path when the yarn pilling occurs;

[0036] Figure 4 In a preferred embodiment of the present invention, it is a schematic diagram of the voltage distribution on each pixel receiving tube when the yarn pilling occurs;

[0037] Figure 5 In a preferred embodiment of the present invention, it is a schematic diagram of the optical path when the yarn is under high tension;

[0038] Figure 6 In a preferred embodiment of the present invention, it is a schematic diagram of the voltage distribution on each pixel receiving tube when the yarn is under high tension; wherein, Figure 2 , Figure 4 and Figure 6 the height in represents the magnitude of the voltage.

[0039] Figure 7 In a preferred embodiment of the present invention, it is a structural block diagram of the data processing module;

[0040] Figure 8 In a preferred embodiment of the present invention, it is a schematic flow diagram of a textile yarn detection method based on a linear array optoelectronic sensor. Specific Embodiments

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0043] Next, the present invention will be further described in conjunction with the accompanying drawings and specific embodiments, but it is not a limitation of the present invention.

[0044] In a preferred embodiment of the present invention, in view of the above problems existing in the prior art, a textile yarn detection system based on a linear array optoelectronic sensor is provided, as Figure 1 shown, including:

[0045] A light source module 1, arranged on one side of the detection area, for emitting light towards the detection area;

[0046] A linear array sensing module 2, arranged on the other side of the detection area opposite to the light source module 1, for generating corresponding linear array voltage signals according to the change in the light intensity received by each pixel receiving tube 21 when the yarn A1 passes through the detection area;

[0047] A data processing module 3, which is respectively connected to the light source module 1 and the linear array sensing module 2, is configured to generate linear image data according to the received linear array voltage signal and process the linear image data to detect the yarn state.

[0048] Specifically, the system shown in the embodiments of the present invention mainly consists of three parts: a light source module 1, a linear array sensing module 2, and a data processing module 3, to realize real-time monitoring of the yarn state.

[0049] Among them, the light source module 1 includes a transmitting tube 11 and a lens 12. The transmitting tube 11 emits a stable and uniform light source to the detection area. After the light source 11 passes through the lens 12, it cooperates with the linear array sensing module 2 to form a detection optical path. In this embodiment, the light source module 1 can provide a specific wavelength light source that matches the linear array sensing module 2. The specific wavelength can be selected according to the optimal working wavelength of the linear array sensing module 2 to improve the quality of the detection signal, reduce noise interference, and thus ensure the accuracy and reliability of the detection result.

[0050] The linear array sensing module 2 is arranged on the other side of the detection area and is arranged opposite to the light source module 1. The linear array photoelectric sensor in the linear array sensing module 2 is composed of a plurality of pixel receiving tubes 21 (P1, P2,..., Pn) arranged, which can capture the precise position and shape of the yarn A1 in the detection area, and helps to more accurately detect the position offset, jitter, and deformation of the yarn A1. The light source is emitted from the light source module 1 and is received by a plurality of pixel receiving tubes 21 after passing through the detection area to generate corresponding signals.

[0051] When there is a yarn A1 in the detection area, the light source passing through the detection area will be affected by the yarn A1 and change, resulting in a decrease in the voltage received by the pixel receiving tube 21 corresponding to the position where the yarn A1 is located compared to the case where there is no yarn A1, thereby changing the voltage distribution state of the light source on each pixel receiving tube 21.

[0052] In the embodiments of the present invention, an example is given where the pixel receiving tube 21 is set to 8.

[0053] As Figure 2 shown, if the voltage distribution on some pixel receiving tubes 21 decreases compared to the reference state when there is no yarn A1, it can be determined that there is a yarn A1 in the current detection area.

[0054] If the voltage distribution on all pixel receiving tubes 21 is consistent with the reference state when there is no yarn A1, it can be determined that there is no yarn A1 in the current detection area. Considering that the system of the present invention is designed specifically for monitoring the quality of the yarn A1 when passing through the detection area, the presence of the yarn A1 is a preset premise. Therefore, once the system determines that the yarn A1 does not exist, it actually means that the yarn A1 has broken or snapped at this moment.

[0055] As Figure 3 shown, when there is a pilling phenomenon on the yarn A1, the pilling area A2 will also have a certain impact on the light transmission effect of the light source, resulting in a decrease in the voltage on the pixel receiving tube 21 corresponding to the position of the pilling area A2. However, the voltage reduction amplitude caused by the pilling area A2 is usually less than the impact of the yarn A1 itself on light transmission. As Figure 4 shown, the voltage distribution of the pilling area A2 and the non-pilling area A2 on the yarn A1 is also different. When the yarn A1 passes through the detection area, if the voltage value of a certain area is lower than the voltage reference value corresponding to the normal yarn A1, but the reduction amplitude is not enough to indicate that it is caused by the yarn A1 itself, then it can be preliminarily judged that there may be a pilling phenomenon in this area. Therefore, the change in the voltage distribution of the pixel receiving tube 21 can be used to distinguish the normal yarn A1 or the pilling yarn A1.

[0056] Furthermore, after confirming the presence of pilling on the yarn A1, the size of the pilling area A2 and the number of pilling areas A2 per unit length on the yarn A1 can be further judged as the quality judgment criteria. For example, the size of the pilling area A2 can be estimated according to the number of pixels occupied by the pilling area A2 in the voltage distribution diagram. For another example, by recording the occurrence frequency of the pilling area A2 on the yarn A1 passing continuously through the detection area and combining with the moving speed of the yarn A1, the number of pilling areas A2 per unit length of the yarn A1 can be counted.

[0057] As Figure 5 shown, when the tension of the yarn A1 changes, the thickness and vibration frequency / amplitude of the spun yarn will both change. Specifically manifested as: the diameter of the yarn A1 will decrease due to the increase in tension, and vice versa. At the same time, when the tension increases, the vibration tends to be stable, the frequency may decrease and the amplitude decreases; when the tension decreases, more frequent vibrations and high amplitudes may be caused. Similarly, as Figure 6 shown, the voltage distribution of the corresponding pixel receiving tubes 21 is also different from the voltage distribution of the yarn A1 under normal tension as Figure 2 shown.

[0058] Furthermore, historical data and machine learning models can also be introduced to realize the prediction and trend analysis of the yarn tension change. By collecting historical data on the yarn tension change over a period of time, including information such as voltage distribution patterns, vibration frequencies, and amplitudes under different tensions, a database with rich features is constructed. Subsequently, machine learning algorithms (such as support vector machines, neural networks, etc.) are used to train the database to establish a mapping relationship model between the tension change and the sensor output signal.

[0059] When new sensor data is input, the model can predict the current yarn tension state and its possible future change trends based on the learned patterns, providing strong support for timely adjusting the spinning process parameters and maintaining the quality stability of yarn A1.

[0060] The data processing module 3 can receive the linear voltage signals from the linear sensor module 2 and then generate linear image data using these signals. By adopting linear sensor technology and combining it with image processing technology, the state detection of yarn A1 within the detection area is realized, including but not limited to information such as the breakage, pilling, thickness change, and tension state of yarn A1.

[0061] Furthermore, the data processing module 3 can also quantitatively evaluate the quality of yarn A1 according to the yarn state, such as the breakage of yarn A1, the size of the pilling area A2, and the number of pilling areas A2 per unit length of yarn A1. When the breakage or pilling area A2 of yarn A1 is too large or the number of pilling areas A2 per unit length of yarn A1 is too many, an alarm or prompt is issued to facilitate timely taking measures for quality improvement.

[0062] Furthermore, the data processing module 3 can also configure the parameters of the light source module 1 and the linear sensor module 2 to adjust the light source parameters and the operating parameters of the linear optoelectronic sensor.

[0063] The light source parameters include but are not limited to controlling whether the light source emits and the light intensity of the light source, so as to further optimize the quality of the detection signal according to actual requirements and environmental conditions. For example, in the case where the color of yarn A1 is lighter or the background light is stronger, the light intensity of the light source can be increased to improve the contrast of the detection signal; while in the case where the color of yarn A1 is darker or the background light is weaker, the light intensity of the light source can be reduced to avoid overexposure or signal loss.

[0064] The operating parameters of the linear optoelectronic sensor include but are not limited to parameters such as sensor gain and scanning frequency.

[0065] Furthermore, the direction after the arrangement of all pixel receiving tubes 21 is set perpendicular to the advancing direction of yarn A1, which can ensure that any slight position deviation or thickness change of yarn A1 can be accurately captured by the pixel receiving tubes 21 when passing through the detection area, so as to more accurately capture the state changes of yarn A1 during the advancing process.

[0066] As a preferred implementation manner, among them, the linear sensor module 2 includes linear optoelectronic sensors such as complementary metal oxide semiconductor (CMOS) linear sensors or charge coupled device (CCD) image sensors.

[0067] Specifically, CMOS linear array sensors have advantages such as low power consumption and high integration, and can be applied to application scenarios with strict requirements for real-time performance and power consumption; while CCD image sensors perform excellently in image quality and color restoration, and are suitable for situations with high requirements for image details. Both of these sensors have characteristics such as high resolution, high sensitivity, and low noise, and can achieve precise monitoring of the yarn state.

[0068] Furthermore, after the system is powered on, first adjust the settings of the linear array optoelectronic sensor to ensure that it is in the best state for measuring yarn A1. Specifically, start the linear array optoelectronic sensor to the self-adjustment mode, set the light intensity of the emitting tube (such as the initial light intensity parameter L0) and the signal channel gain (such as the initial gain G0) to calibrate the sensor, so that the voltage of the pixel receiving tube 21 with the maximum voltage reaches a certain proportion of the full-scale voltage, such as 90%, to ensure that the sensor is not saturated and has a certain signal-to-noise ratio, thereby improving the measurement accuracy.

[0069] Next, set the LED drive output of the emitting tube 11 to 0 for subsequent settings under the condition of no light. According to the previously determined signal channel gain setting, set the light intensity to 0 as well. At this time, collect the voltages of each pixel receiving tube 21 on the linear array optoelectronic sensor to form a voltage array, denoted as VP = [V1, V2,... Vn], where the subscript n is the number of pixel receiving tubes 21. The voltage array VP represents the signals on each pixel receiving tube 21 in the absence of modulated light, and the voltages of these signals include noise, dark current, and the voltage formed by ambient light on the linear array optoelectronic sensor.

[0070] Through the above voltage array VP, the influence of ambient light changes on the sensor can be reduced, and interference factors such as dust can be reduced through dynamic self-adjustment, with strong anti-interference ability.

[0071] The above adjustment steps of the linear array optoelectronic sensor can be carried out in two cases: when there is spun yarn within the measurement range of the sensor and when there is no spun yarn within the measurement range of the sensor.

[0072] As a preferred embodiment, as Figure 7 shown, the data processing module 3 includes:

[0073] A calculation unit 31 for calculating the difference between the maximum voltage and the minimum voltage in the linear array voltage signal;

[0074] A judgment unit 32, connected to the calculation unit 31, for judging whether the difference exceeds a preset threshold, and when the difference exceeds the preset threshold, determining that yarn A1 exists; and when the difference does not exceed the preset threshold, determining that yarn A1 is broken.

[0075] Specifically, in this embodiment, the breakage detection of yarn A1 can be achieved by measuring the voltage change or voltage distribution when there is no spun yarn and when there is spun yarn, and setting a reasonable threshold. When the voltage change exceeds this threshold, it is determined that yarn A1 has broken or there is a broken filament phenomenon.

[0076] It should be noted that during the normal movement of yarn A1, yarn A1 will vibrate, resulting in continuous changes in the voltage distribution on each pixel receiving tube 21 of the sensor.

[0077] In this embodiment, based on this dynamically changing linear array voltage signal, at the same moment, it is determined whether yarn A1 exists by judging whether the difference between the maximum voltage and the minimum voltage among all pixel receiving tubes 21 exceeds a preset threshold.

[0078] When the difference exceeds the preset threshold, it indicates that yarn A1 exists;

[0079] When the difference does not exceed the preset threshold, it indicates that yarn A1 does not exist, that is, it is determined that yarn A1 has broken or there is a broken filament phenomenon.

[0080] Furthermore, in order to further improve the reliability of the breakage detection of yarn A1, it can also be judged based on linear image data. For example, the voltage change amount of each pixel receiving tube 21 in the linear array photoelectric sensor, linear image data, centroid position of the light spot, position change of the pixels blocked by yarn A1, and position change frequency can be measured simultaneously to comprehensively judge whether yarn A1 has broken, thereby further improving the detection reliability.

[0081] By obtaining the complete contour, position data, and position change data of yarn A1, the breakage detection of yarn A1 can more effectively distinguish the normal movement of yarn A1 from the actual wire break situation, reduce false alarms and missed alarms, and improve the accuracy of wire break detection.

[0082] The present invention further improves the detection stability and reliability through image processing technology filtering.

[0083] As a preferred embodiment, the data processing module 3 further includes:

[0084] A signal processing unit 33 for performing zero-point removal processing on the linear array voltage signal to obtain a first signal;

[0085] An imaging unit 34, connected to the signal processing unit 33, for performing imaging processing according to the first signal to generate linear image data.

[0086] As a preferred embodiment, the signal processing unit 33 is configured to calculate the difference between the linear array voltage signal and the reference signal to obtain a first signal, where the reference signal is the signal output by each pixel of the linear array sensing module 2 under the condition of no light source.

[0087] In this embodiment, the reference signal is the above-mentioned voltage array VP.

[0088] Specifically, under the conditions of the same gain (G0) and light intensity setting (L0), the signals of each pixel receiving tube 21 on the linear array optoelectronic sensor are collected in real time. Subsequently, using the previously obtained voltage array VP = [V1, V2,... Vn], the difference calculation is performed on the signals currently collected by each pixel receiving tube 21, that is, the current signal minus the corresponding reference signal value, and the result is the first signal, which reflects the voltage change caused only by the current light condition, so as to remove the influence of ambient light interference and dark current noise and improve the signal-to-noise ratio.

[0089] The imaging unit 34 performs imaging processing based on these first signals and converts the voltage signal into linear image data. Since most of the noise has been removed from the first signal, the imaging unit can generate a clearer and more accurate linear image, and this image data dynamically reflects the real-time state of the spun yarn passing through the sensor.

[0090] Furthermore, before imaging, the data processing module 3 can also perform analog-to-digital conversion on the analog signal collected by the linear array optoelectronic sensor, convert it into a digital signal, and further obtain the above-mentioned linear image data through digital signal processing.

[0091] In addition to detecting the presence or absence of the yarn A1, multiple parameters such as the thickness change, surface defects, and tension change of the yarn A1 can also be monitored, providing more data support for quality control.

[0092] As a preferred embodiment, the data processing module 3 further includes:

[0093] An image preprocessing unit 35 that preprocesses the linear image data to obtain preprocessed linear image data;

[0094] A feature extraction unit 36, connected to the image preprocessing unit 35, for extracting features from the preprocessed linear image data to obtain feature information;

[0095] An analysis unit 37, connected to the feature extraction unit 36, for analyzing according to the feature information to determine the yarn state.

[0096] Specifically, in this embodiment, the data processing module 3 can perform image preprocessing, feature extraction, and analysis on the collected linear image data, and detect the breakage, pilling state, and tension change state of the yarn A1 in real time.

[0097] Through image preprocessing, key parameters such as the size, swing frequency, position change, and size change of the spun yarn are determined according to the imaging situation.

[0098] An algorithm is used for gray-scale adjustment and contrast enhancement to highlight the characteristic information of yarn A1. The characteristic information includes but is not limited to the contour, texture, thickness change, etc. of yarn A1. Through gray-scale adjustment, the part of yarn A1 in the image can be made clearer. Contrast enhancement helps to distinguish the difference between yarn A1 and the background, further improving the quality of the image.

[0099] The analysis unit receives the characteristic information from the feature extraction unit and conducts in-depth analysis based on this information. The analysis content includes the breakage state, pilling situation, and tension change of yarn A1, etc. By comparing with preset standards or models, the analysis unit can accurately judge the current state of yarn A1 and output corresponding analysis results. These analysis results can be used for quality control of yarn A1, monitoring of the production process, and fault warning, etc., providing strong support for the automation and intelligence of yarn A1 production.

[0100] Furthermore, the data processing module 3 adopts AI algorithms such as machine learning models to improve the recognition accuracy of yarn pilling and abnormal tension, and enhance the detection performance.

[0101] During the model training process, a large amount of image data of normal and abnormal yarns is collected. These data cover the imaging situations of yarn A1 in different states, including normal yarn images, pilled yarn images, and yarn images with abnormal tension, etc. Then, a convolutional neural network (CNN) model is trained using these image data. The convolutional neural network is a deep learning algorithm with powerful image feature extraction and classification capabilities. Through training, the model can learn the key features in the yarn images and achieve automatic recognition and classification of pilling and abnormal tension.

[0102] During the model training process, a supervised learning method can be adopted, that is, using image data with known labels for training. These labels indicate the state (normal, pilled, or abnormal tension) of yarn A1 in the image. By continuously optimizing the parameters of the model, it can more accurately classify newly input yarn images.

[0103] After training is completed, the trained convolutional neural network model is used to conduct real-time detection on the linear image data of the new yarn A1. The model can output the state information of yarn A1, including whether there is pilling, whether the tension is abnormal, etc. The system can predict possible quality problems based on these output information and intervene in advance.

[0104] When the model detects pilling on yarn A1, the system can immediately issue an alarm to prompt the operator to maintain the equipment or replace yarn A1. Similarly, when the model detects abnormal tension, the system can automatically adjust the parameters of the tension controller to restore the normal tension state of yarn A1.

[0105] As a preferred embodiment, a pilling monitoring model 372 is preset in the analysis unit. The pilling monitoring model 372 is used to determine the pilling monitoring result according to the characteristic information. The pilling monitoring result includes at least the pilling area A2, the type of each pilling area A2, and the size distribution of the pilling.

[0106] In this embodiment, the types of the pilling area A2 include but are not limited to yarn hairiness, defects (such as knots, thick places, and thin places), and surface damage.

[0107] Furthermore, in order to achieve accurate detection of the pilling state, edge detection and texture analysis algorithms can be used for pilling state detection to extract the characteristic information on the surface of yarn A1.

[0108] Yarn hairiness is the fibers protruding from the surface of yarn A1. The fine changes in the contour of yarn A1 can be detected by the edge detection algorithm to identify the hairiness on the surface of yarn A1.

[0109] The texture analysis algorithm detects surface damage, such as wear and breakage of yarn A1, by analyzing the texture and light reflection characteristics of the surface of yarn A1.

[0110] In addition, a sudden change in the diameter of yarn A1 can also be detected, thereby identifying defects, such as areas with abnormal local thicknesses, such as knots, thick places, and thin places.

[0111] After obtaining the characteristic information on the surface of yarn A1, these information are used for imaging to identify and locate the pilling area A2, and analyze the number, size, distribution, and passing time through the sensor of the pilling.

[0112] Finally, according to the preset standard, the severity of the pilling can be evaluated, and the corresponding quality evaluation result can be provided to timely detect yarn quality problems and provide a strong basis for quality control and process optimization in the production process.

[0113] As a preferred embodiment, a tension monitoring model 371 is preset in the analysis unit. The tension monitoring model 371 is used to determine the tension change amount according to the characteristic information.

[0114] Specifically, during the advancing movement of yarn A1, minute vibrations will occur. The change in tension will affect the frequency and amplitude of the vibrations, and at the same time, it will also cause a slight deviation in the spatial position of yarn A1. Specifically, when the yarn tension increases, yarn A1 will be stretched, resulting in a slightly thinner diameter, and at the same time, the vibration frequency may increase while the amplitude decreases. When the tension is too high, yarn A1 shows a straighter and more stable state. On the contrary, when the yarn tension decreases, yarn A1 will retract, resulting in a thicker diameter, and at the same time, the vibration frequency decreases while the amplitude increases. When the tension is too low, yarn A1 will show bending or jittering phenomena.

[0115] Tension monitoring is achieved by detecting the position change and vibration characteristics of yarn A1. Linear image data is used to detect minute changes in the spatial position and shape of yarn A1, measure the vibration frequency and amplitude characteristics of yarn A1, calculate the amount of tension change, and identify abnormal tension.

[0116] By comparing the vibration characteristics under normal conditions with those under abnormal conditions, the system can promptly detect abnormal tension and take corresponding handling measures. When it is monitored that the tension exceeds a preset certain range, the system will automatically adjust the parameters of the tension controller to ensure that the yarn tension is maintained at a stable and appropriate level.

[0117] Finally, by combining historical data and a preset tension monitoring model, it is possible to predict the change trend of yarn tension and detect potential tension problems in advance.

[0118] As a preferred implementation manner, among them, the data processing module 3 is also used to generate real-time feedback information according to the yarn state, and generate corresponding alarm information when the yarn state is abnormal.

[0119] Specifically, in this embodiment, the data processing module 3 issues alarm information, automatically adjusts the parameters of the production equipment, or executes control instructions such as shutdown according to the analysis results, such as when abnormal situations (such as the breakage of yarn A1, severe pilling, or the tension exceeding the set range) are detected.

[0120] The data processing module 3 can also transmit the analysis results to the host computer or the display.

[0121] Furthermore, the system also includes a power supply module 4 and a communication output module 5. The power supply module 4 is electrically connected to the data processing module 3 and is used to supply power to the entire system; the communication output module 5 is used to realize data interaction between the data processing module 3 and the host computer or the production management system, and realize data storage, display, and further analysis.

[0122] The present invention also provides a textile yarn detection method based on a linear array optoelectronic sensor, which is applied to the textile yarn detection system based on a linear array optoelectronic sensor as described above, as Figure 8 shown, the method includes:

[0123] S100, the light source module 1 emits light towards the detection area;

[0124] S200, when the yarn A1 passes through the detection area, the linear array sensing module 2 generates corresponding linear array voltage signals according to the light intensity changes received by each pixel receiving tube 21;

[0125] S300, generate linear image data based on the received linear array voltage signals, and process the linear image data to detect the yarn state.

[0126] The present invention provides an efficient and accurate textile yarn detection system and method. By utilizing the advantages of linear array optoelectronic sensors and combining advanced signal processing and machine learning technologies, it can accurately detect the breakage and pilling states of the yarn A1 simultaneously, and monitor the yarn tension to improve the quality control level and production efficiency of textile production.

[0127] Regarding more implementation details of this method, the system has been disclosed, and will not be elaborated in this embodiment.

[0128] The advantages or beneficial effects of adopting the above technical solutions are as follows: The present invention realizes high-precision detection of yarn states by integrating a light source module, a linear array sensing module, and a data processing module, and can simultaneously monitor the breakage, pilling states, and tension changes of the yarn, significantly improving the quality control level and production efficiency of textile production; at the same time, combined with image processing technology, it can more effectively distinguish normal yarn movement from broken yarn situations, reduce false alarms and missed detections, and further improve the stability and reliability of detection.

[0129] The above are only preferred embodiments of the present invention, and do not limit the implementation manners and protection scope of the present invention accordingly. For those skilled in the art, it should be realized that all equivalent replacements and obvious changes made by using the content of this specification and the drawings should be included in the protection scope of the present invention.

Claims

1. A textile yarn detection system based on a linear array photoelectric sensor, characterized in that: include: A light source module, disposed at one side of the detection area, for emitting light toward the detection area; A linear array sensor module is arranged on the other side of the detection area opposite to the light source module, and is used to generate a corresponding linear array voltage signal according to the change of light intensity received by each pixel receiving tube when the yarn passes through the detection area; The data processing module is connected to the light source module and the linear array sensing module respectively, and is used to generate linear image data according to the received linear array voltage signal, and process the linear image data to detect the yarn state.

2. The textile yarn detection system based on linear array photoelectric sensor according to claim 1 is characterized in that: The linear array sensing module includes a complementary metal oxide semiconductor linear array sensor or a charge coupled device image sensor.

3. The textile yarn detection system based on linear array photoelectric sensor according to claim 1 is characterized in that: The data processing module comprises: A calculation unit, used for calculating the difference between the maximum voltage and the minimum voltage in the linear array voltage signal; A judging unit is connected to the calculating unit and is used to judge whether the difference exceeds a preset threshold value, and to judge that the yarn exists when the difference exceeds the preset threshold value; and to judge that the yarn is broken when the difference does not exceed the preset threshold value.

4. The textile yarn detection system based on linear array photoelectric sensor according to claim 1 is characterized in that: The data processing module also includes: A signal processing unit, used for performing a zero-point removal process on the linear array voltage signal to obtain a first signal; An imaging unit is connected to the signal processing unit and is used to perform imaging processing according to the first signal to generate the linear image data.

5. The textile yarn detection system based on linear array photoelectric sensor according to claim 4 is characterized in that: The signal processing unit is used to calculate the difference between the linear array voltage signal and a reference signal to obtain a first signal, wherein the reference signal is a signal output by each pixel of the linear array sensor module in the absence of a light source.

6. The textile yarn detection system based on linear array photoelectric sensor according to claim 1, characterized in that: The data processing module also includes: An image preprocessing unit, which preprocesses the linear image data to obtain preprocessed linear image data; A feature extraction unit, connected to the image preprocessing unit, for extracting features from the preprocessed linear image data to obtain feature information; The analyzing unit is connected to the feature extracting unit and is used for analyzing according to the feature information to determine the yarn state.

7. The textile yarn detection system based on linear array photoelectric sensor according to claim 6 is characterized in that: The analysis unit is pre-installed with a pilling monitoring model, which is used to determine a pilling monitoring result according to the feature information, wherein the pilling monitoring result at least includes pilling areas, types of each pilling area, and size distribution of pilling.

8. The textile yarn detection system based on linear array photoelectric sensor according to claim 6, characterized in that: A tension monitoring model is preset in the analysis unit, and the tension monitoring model is used to determine the tension change amount according to the characteristic information.

9. The textile yarn detection system based on linear array photoelectric sensor according to claim 6, characterized in that: The data processing module is also used to generate real-time feedback information according to the yarn state, and to generate corresponding alarm information when the yarn state is abnormal.

10. A textile yarn detection method based on a linear array photoelectric sensor, characterized in that: Applied in a textile yarn detection system based on a linear array photoelectric sensor as claimed in any one of claims 1 to 9, the method comprises: The light source module emits light toward the detection area; When the yarn passes through the detection area, the linear array sensing module generates a corresponding linear array voltage signal according to the change in light intensity received by each pixel receiving tube; Linear image data is generated according to the received linear array voltage signal, and the linear image data is processed to detect the yarn state.

Images