Nonwoven fabric defect detection method

Abstract

The present application provides a non-woven fabric defect detection method, which relates to the field of defect detection technology. The method comprises the following steps: obtaining characterization features of the non-woven fabric; based on a preset non-woven fabric pre-generated image module, using the characterization features of the non-woven fabric, generating pre-generated non-woven fabric images of the current non-woven fabric under different backlight intensities, wherein the pre-generated non-woven fabric images include pre-generated non-woven fabric defect images and pre-generated non-woven fabric non-defect images; inputting the pre-generated non-woven fabric defect images under each backlight intensity into a preset defect recognition model for recognition, and selecting a pre-preferred backlight intensity; in actual detection, obtaining non-woven fabric non-defect images under multiple preset backlight intensities; calculating the deviation value between the non-woven fabric non-defect image actually obtained and the pre-generated non-woven fabric non-defect image under the corresponding backlight intensity; and obtaining the actual detection backlight intensity based on the deviation value. The present application can more accurately detect defects in non-woven fabrics.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular to a method for detecting defects in non-woven fabrics. Background Art

[0002] As an important industrial material, nonwovens are widely used in healthcare, filtration materials, geotextiles, clothing, and household products. Their quality directly impacts product performance and safety. Therefore, defect detection of nonwovens during the production process is crucial.

[0003] With the development of computer vision and artificial intelligence technologies, image recognition methods based on machine learning and deep learning have gradually been applied to the field of non-woven fabric defect detection. These methods can improve the accuracy and efficiency of detection to a certain extent by training models.

[0004] However, backlight intensity has a significant impact on the appearance of non-woven fabric defects, and the optical properties of non-woven fabrics are affected by factors such as material type, fiber size, arrangement and arrangement density. Some non-woven fabrics can also produce fluorescence.

[0005] Non-woven fabrics with strong reflectivity will weaken the backlight effect, while non-woven fabrics that can stimulate fluorescence will brighten the backlight effect. This will affect the backlight projection. Using a uniform backlight intensity will cause some defects to not receive appropriate backlight projection, reducing the possibility of recognition. Summary of the Invention

[0006] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a non-woven fabric defect detection method that can more accurately detect defects in non-woven fabrics.

[0007] The present application provides a non-woven fabric defect detection method, which comprises the following steps:

[0008] Obtain the surface fiber design structure and material properties of the current non-woven fabric to obtain the characterization characteristics of the non-woven fabric;

[0009] Based on a preset non-woven fabric pre-generated image module, using the characterization features of the non-woven fabric, generating pre-generated non-woven fabric images of the current non-woven fabric under different backlight intensities, the pre-generated non-woven fabric images including pre-generated non-woven fabric defect images and pre-generated non-woven fabric defect-free images;

[0010] Input the pre-generated non-woven fabric defect image under each backlight intensity into the preset defect recognition model for recognition, and select the backlight intensity corresponding to the pre-generated non-woven fabric defect image with the highest recognition rate as the pre-optimal backlight intensity;

[0011] In actual inspection, defect-free images of nonwoven fabrics are obtained under multiple preset backlight intensities;

[0012] Calculating a deviation value between an actually acquired non-woven fabric defect-free image and a pre-generated non-woven fabric defect-free image under a corresponding backlight intensity;

[0013] According to the deviation value, the pre-optimized backlight intensity is adjusted by a preset backlight intensity adjustment function to obtain the actual detected backlight intensity;

[0014] The non-woven fabric is illuminated by utilizing the actual detected backlight intensity, and defects of the non-woven fabric are detected using a camera and a preset defect recognition model.

[0015] Optionally, the surface fiber design structure includes fiber size, arrangement orientation and arrangement density, and the material properties include non-woven fabric material type and fluorescence efficiency;

[0016] The preset non-woven fabric pre-generated image module is constructed by the following steps:

[0017] The basic network structure generation module uses 3D modeling software to establish the basic network structure of non-woven fabrics based on the surface fiber design structure;

[0018] Defect structure generation module, which uses 3D modeling software to select whether to insert defect structures into the basic network structure;

[0019] Setting the application material and fluorescence efficiency parameters of the basic network structure in the three-dimensional modeling software according to the type of non-woven fabric material and the fluorescence efficiency;

[0020] Add backlight source to the basic network structure;

[0021] Changing the intensity of the backlight source and rendering the basic network structure using an optical rendering engine, and obtaining non-woven fabric rendering images under different backlight intensities by setting a virtual camera;

[0022] Constructing an optical mask processing model, wherein the network framework of the optical mask processing model is a generative adversarial network, collecting multiple actual non-woven fabric images and corresponding non-woven fabric rendering images, using the actual non-woven fabric surface images as labels and the corresponding non-woven fabric rendering images as input, and training the generative adversarial network to obtain the optical mask processing model;

[0023] The non-woven fabric rendering images under different backlight intensities are input into the optical mask processing model for processing to obtain pre-generated non-woven fabric images under different backlight intensities.

[0024] Optionally, the preset defect recognition model is trained by the following steps:

[0025] The network framework of the defect recognition model is a convolutional neural network;

[0026] A plurality of non-woven fabric defect images with different defect types are collected, and the plurality of non-woven fabric defect images are used as input and the defect type is used as a label to train a defect recognition model.

[0027] Optionally, calculating a deviation between an actually acquired non-woven fabric defect-free image and a pre-generated non-woven fabric defect-free image under a corresponding backlight intensity, and adjusting the pre-optimized backlight intensity according to the deviation using a preset backlight intensity adjustment function to obtain an actual detected backlight intensity, comprises the following steps:

[0028] The deviation value between the actually acquired defect-free non-woven fabric image and the pre-generated defect-free non-woven fabric image under the corresponding backlight intensity is calculated by a structural similarity algorithm;

[0029] Determine the backlight intensity corresponding to the minimum deviation value according to the deviation value under each preset backlight intensity;

[0030] The preset backlight intensity adjustment function is:

[0031]

[0032]

[0033] in, To actually detect the backlight intensity, To pre-optimize the backlight intensity, is the backlight intensity corresponding to the minimum deviation value, and c is the first empirical parameter.

[0034] The technical solution provided by this application has the following advantages compared with the existing technology:

[0035] One of its beneficial technical effects is that since the fiber thickness, arrangement and material properties of non-woven fabrics affect the reflection and fluorescence effects of light, the projection of backlight is affected, which in turn affects the detectability of defects. The traditional method of fixing the backlight intensity cannot adapt to the detection needs of different non-woven fabrics.

[0036] In order to solve this problem, the present application first obtains the surface fiber design structure and material properties of the current non-woven fabric to obtain the characterization characteristics of the non-woven fabric, which can be used to reflect the response characteristics of the non-woven fabric to light.

[0037] Based on this, a pre-set non-woven fabric pre-generated image module is used to generate pre-generated non-woven fabric images of the current non-woven fabric at different backlight intensities, including defective and non-defective images. The pre-generated defect images at each backlight intensity are input into a pre-set defect recognition model, and the defect recognition rate corresponding to each backlight intensity is evaluated. The backlight intensity with the highest recognition rate is selected as the pre-optimal backlight intensity, resulting in the pre-optimal backlight intensity.

[0038] Furthermore, considering the influence of actual ambient light, during the actual inspection process, multiple defect-free images of nonwoven fabrics are acquired under preset backlight intensities. The deviation between these actual images and the pre-generated defect-free images is calculated. Based on these deviations, a preset backlight intensity adjustment function is used to precisely adjust the pre-optimized backlight intensity to obtain the actual inspection backlight intensity.

[0039] Finally, the nonwoven fabric is illuminated with the adjusted actual detection backlight intensity, and defects are detected using a camera and a preset defect recognition model. This method fully considers the optical properties of the nonwoven fabric and the actual detection environment. By automatically optimizing the backlight intensity, it improves the accuracy and reliability of defect detection and resolves the detection errors caused by inappropriate backlight intensity in traditional methods.

[0040] Therefore, the non-woven fabric defect detection method provided in the present application can more accurately detect defects in non-woven fabrics.

[0041] The second beneficial technical effect is that, in actual applications, due to the influence of changes in ambient lighting, the pre-determined pre-optimized backlight intensity may not maintain the optimal effect under all detection conditions, resulting in a deviation between the pre-generated defect-free image and the actual defect-free image obtained. When the backlight intensity point with the smallest deviation value deviates far from the pre-optimized backlight intensity, it means that the current pre-optimized backlight intensity is not fully adapted to the actual detection environment. If not adjusted, it may lead to a decrease in the accuracy of defect detection. To solve this problem, the present application obtains actual defect-free images under multiple preset backlight intensities and compares them with the corresponding pre-generated defect-free images to calculate the deviation value. Based on these deviation values, a preset backlight intensity adjustment function is used to dynamically adjust the pre-optimized backlight intensity to make it closer to the direction of the actual minimum deviation point, and the amplitude of the adjustment is adjusted according to the size of the deviation value. Specifically, when the backlight intensity point with the smallest deviation value is far away from the pre-optimized backlight intensity, the adjustment function will adjust the pre-optimized backlight intensity more significantly to minimize the deviation as much as possible; when the point with the smallest deviation value is close to the pre-optimized backlight intensity, the adjustment amplitude is correspondingly reduced to reduce the possibility of deviation caused by the adjustment. This dynamic adjustment mechanism can effectively compensate for the influence of external factors such as ambient light, ensure that the backlight intensity setting is more accurate, and reduce the occurrence of false detection and missed detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Flowchart of the non-woven fabric detection method provided in the embodiment of the present application. DETAILED DESCRIPTION

[0043] The technical solution in this application will be described below with reference to the accompanying drawings.

[0044] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application may also be implemented in other ways than those described herein. It is apparent that the embodiments described in the specification are only some of the embodiments of the present application, not all of them. It should be noted that the embodiments of the present application and the features therein may be combined with each other unless there is a conflict.

[0045] like Figure 1 As shown, the present application provides a non-woven fabric defect detection method, which includes the following steps:

[0046] S101: Obtain the surface fiber design structure and material properties of the current non-woven fabric to obtain the characterization characteristics of the non-woven fabric;

[0047] Specifically, the surface fiber design structure includes fiber size, arrangement orientation and arrangement density, and the material properties include non-woven fabric material type and fluorescence efficiency.

[0048] These parameters need to be manually input and set according to the specific parameters of the current non-woven fabric production.

[0049] S102: Based on a preset non-woven fabric pre-generated image module, using the characterization features of the non-woven fabric, generating pre-generated non-woven fabric images of the current non-woven fabric under different backlight intensities, the pre-generated non-woven fabric images including pre-generated non-woven fabric defect images and pre-generated non-woven fabric defect-free images;

[0050] The preset non-woven fabric pre-generated image module is constructed by the following steps:

[0051] The basic network structure generation module uses 3D modeling software to establish the basic network structure of non-woven fabrics based on the surface fiber design structure.

[0052] Specifically, the three-dimensional modeling software is 3DEXPERIENCE.

[0053] Among them, the basic network structure of the non-woven fabric can be imported into the structural model designed by the user before production, or the established non-woven fabric basic network structure template can be transformed according to the actual fiber size, arrangement orientation and arrangement density to obtain the basic network structure of this non-woven fabric.

[0054] Defect structure generation module, which uses 3D modeling software to select whether to insert defect structures into the basic network structure;

[0055] Specifically, it realizes collecting multiple types of defect structures, and randomly inserting random types and random numbers of defect structures into the basic network structure according to whether to generate a pre-generated non-woven fabric defect image or a pre-generated non-woven fabric defect-free image;

[0056] After the defect structure is inserted, the insertion position of each defect structure and the type of defect structure corresponding to the insertion position are recorded for verification during subsequent defect identification when the pre-optimized backlight intensity is selected.

[0057] The application material and fluorescence efficiency of the basic network structure are set in the three-dimensional modeling software according to the type of non-woven fabric material and the fluorescence efficiency.

[0058] Add backlight source to the basic network structure;

[0059] The intensity of the backlight source is changed, and the basic network structure is rendered using an optical rendering engine, and a virtual camera is set to obtain non-woven fabric rendering images under different backlight intensities.

[0060] Specifically, the optical rendering engine here is the optical rendering engine provided in 3DEXPERIENCE.

[0061] An optical mask processing model is constructed. The network framework of the optical mask processing model is a generative adversarial network. Multiple actual non-woven fabric images and corresponding non-woven fabric rendering images are collected. The actual non-woven fabric surface images are used as labels and the corresponding non-woven fabric rendering images are used as inputs. The generative adversarial network is trained to obtain the optical mask processing model.

[0062] The non-woven fabric rendering images under different backlight intensities are input into the optical mask processing model for processing to obtain pre-generated non-woven fabric images under different backlight intensities.

[0063] S103: inputting the pre-generated non-woven fabric defect image at each backlight intensity into a preset defect recognition model for recognition, and selecting the backlight intensity corresponding to the pre-generated non-woven fabric defect image with the highest recognition rate as the pre-optimal backlight intensity;

[0064] Specifically, the preset defect recognition model is trained through the following steps:

[0065] The network framework of the defect recognition model is a convolutional neural network;

[0066] A plurality of non-woven fabric defect images with different defect types are collected, and the plurality of non-woven fabric defect images are used as input and the defect type is used as a label to train a defect recognition model.

[0067] In actual detection, before applying the defect recognition model, the image is usually binarized and segmented to identify the area where the abnormal binary points are located as the region of interest.

[0068] The image in the region of interest is then input into the defect recognition model to complete the defect recognition. However, this belongs to the existing technology and will not be described in detail here.

[0069] S104: In actual detection, a camera is used to obtain a plurality of defect-free images of the non-woven fabric under a preset backlight intensity.

[0070] Specifically, the multiple preset backlight intensities here include at least a pre-preferred backlight intensity and multiple left and right backlight intensities. In the embodiment of the present application, To pre-optimize the backlight intensity, is a manually set step size, n is a manually set number, then the set of multiple preset backlight intensities is ( ,…, ,…, ).

[0071] Calculating a deviation value between an actually acquired non-woven fabric defect-free image and a pre-generated non-woven fabric defect-free image under a corresponding backlight intensity;

[0072] According to the deviation value, the pre-optimized backlight intensity is adjusted by a preset backlight intensity adjustment function to obtain the actual detected backlight intensity;

[0073] Specifically, the following steps are included:

[0074] The deviation value between the actually acquired non-woven fabric defect-free image and the pre-generated non-woven fabric defect-free image under the corresponding backlight intensity is calculated by a structural similarity algorithm.

[0075] The structural similarity algorithm is an existing technology for comparing the similarity between images, which will not be described in detail here.

[0076] According to the size of the deviation value under each preset backlight intensity, the backlight intensity corresponding to the minimum deviation value is determined .

[0077] The preset backlight intensity adjustment function is:

[0078]

[0079]

[0080] in, To actually detect the backlight intensity, To pre-optimize the backlight intensity, is the backlight intensity corresponding to the minimum deviation value, and c is the first empirical parameter set artificially.

[0081] S105: irradiating the non-woven fabric with the actual detected backlight intensity, and detecting defects of the non-woven fabric using a camera and a preset defect recognition model.

[0082] This step is actually the same as S103, and the defect recognition model is applied to identify surface defects in the captured non-woven fabric image. This belongs to the existing technology and will not be described in detail here.

[0083] In summary, the non-woven fabric defect detection method provided in the embodiments of the present application has the following beneficial effects:

[0084] One of its beneficial technical effects is that since the fiber thickness, arrangement and material properties of non-woven fabrics affect the reflection and fluorescence effects of light, the projection of backlight is affected, which in turn affects the detectability of defects. The traditional method of fixing the backlight intensity cannot adapt to the detection needs of different non-woven fabrics.

[0085] In order to solve this problem, the present application first obtains the surface fiber design structure and material properties of the current non-woven fabric to obtain the characterization characteristics of the non-woven fabric, which can be used to reflect the response characteristics of the non-woven fabric to light.

[0086] Based on this, a pre-set non-woven fabric pre-generated image module is used to generate pre-generated non-woven fabric images of the current non-woven fabric at different backlight intensities, including defective and non-defective images. The pre-generated defect images at each backlight intensity are input into a pre-set defect recognition model, and the defect recognition rate corresponding to each backlight intensity is evaluated. The backlight intensity with the highest recognition rate is selected as the pre-optimal backlight intensity, resulting in the pre-optimal backlight intensity.

[0087] Furthermore, considering the influence of actual ambient light, during the actual inspection process, multiple defect-free images of nonwoven fabrics are acquired under preset backlight intensities. The deviation between these actual images and the pre-generated defect-free images is calculated. Based on these deviations, a preset backlight intensity adjustment function is used to precisely adjust the pre-optimized backlight intensity to obtain the actual inspection backlight intensity.

[0088] Finally, the nonwoven fabric is illuminated with the adjusted actual detection backlight intensity, and defects are detected using a camera and a preset defect recognition model. This method fully considers the optical properties of the nonwoven fabric and the actual detection environment. By automatically optimizing the backlight intensity, it improves the accuracy and reliability of defect detection and resolves the detection errors caused by inappropriate backlight intensity in traditional methods.

[0089] Therefore, the non-woven fabric defect detection method provided in the present application can more accurately detect defects in non-woven fabrics.

[0090] The second beneficial technical effect is that, in actual applications, due to the influence of changes in ambient lighting, the pre-determined pre-optimized backlight intensity may not maintain the optimal effect under all detection conditions, resulting in a deviation between the pre-generated defect-free image and the actual defect-free image. When the backlight intensity point with the minimum deviation value deviates significantly from the pre-optimized backlight intensity, it indicates that the current pre-optimized backlight intensity is not fully adapted to the actual detection environment. If not adjusted, the accuracy of defect detection may decrease. To address this problem, the present application obtains actual defect-free images under multiple preset backlight intensities and compares them with the corresponding pre-generated defect-free images to calculate deviation values. Based on these deviation values, a preset backlight intensity adjustment function is used to dynamically adjust the pre-optimized backlight intensity to bring it closer to the direction of the actual minimum deviation point, and the adjustment amount is adjusted according to the size of the deviation value. Specifically, when the backlight intensity point with the minimum deviation value is far away from the pre-optimized backlight intensity, the adjustment function will adjust the pre-optimized backlight intensity more significantly to minimize the deviation as much as possible; when the point with the minimum deviation value is close to the pre-optimized backlight intensity, the adjustment amount is reduced accordingly to reduce the possibility of deviation caused by the adjustment. This dynamic adjustment mechanism can effectively compensate for the influence of external factors such as ambient light, ensure that the backlight intensity setting is more accurate, and reduce the occurrence of false detection and missed detection.

[0091] It should be noted that, in this document, relational terms such as "first" and "second" are used solely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Furthermore, the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article, or device comprising the element. Furthermore, in the description of the embodiments of this application, unless otherwise specified, " / " represents or. For example, A / B can represent either A or B. "And / or" herein is merely a description of an associative relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, in the description of the embodiments of the present application, “plurality” refers to two or more than two.

[0092] The foregoing description is intended only to provide specific embodiments of the present application, which will enable those skilled in the art to understand and implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments described herein, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting defects in nonwoven fabrics, characterized in that: The nonwoven fabric defect detection method comprises the following steps: Obtain the surface fiber design structure and material properties of the current non-woven fabric to obtain the characterization characteristics of the non-woven fabric; Based on a preset non-woven fabric pre-generated image module, using the characterization features of the non-woven fabric, generating pre-generated non-woven fabric images of the current non-woven fabric under different backlight intensities, the pre-generated non-woven fabric images including pre-generated non-woven fabric defect images and pre-generated non-woven fabric defect-free images; Input the pre-generated non-woven fabric defect image under each backlight intensity into the preset defect recognition model for recognition, and select the backlight intensity corresponding to the pre-generated non-woven fabric defect image with the highest recognition rate as the pre-optimal backlight intensity; In actual inspection, defect-free images of nonwoven fabrics are obtained under multiple preset backlight intensities; Calculating a deviation value between an actually acquired non-woven fabric defect-free image and a pre-generated non-woven fabric defect-free image under a corresponding backlight intensity; According to the deviation value, the pre-optimized backlight intensity is adjusted by a preset backlight intensity adjustment function to obtain the actual detected backlight intensity; Illuminating the non-woven fabric using the actual detected backlight intensity, and detecting defects in the non-woven fabric using a camera and a preset defect recognition model; Calculating a deviation between an actually acquired non-woven fabric defect-free image and a pre-generated non-woven fabric defect-free image under a corresponding backlight intensity, and adjusting the pre-optimized backlight intensity according to the deviation using a preset backlight intensity adjustment function to obtain an actual detected backlight intensity, comprising the following steps: The deviation value between the actually acquired defect-free non-woven fabric image and the pre-generated defect-free non-woven fabric image under the corresponding backlight intensity is calculated by a structural similarity algorithm; Determine the backlight intensity corresponding to the minimum deviation value according to the deviation value under each preset backlight intensity; The preset backlight intensity adjustment function is: in, To actually detect the backlight intensity, To pre-optimize the backlight intensity, is the backlight intensity corresponding to the minimum deviation value, and c is the first empirical parameter.

2. The nonwoven fabric defect detection method according to claim 1, characterized in that: The surface fiber design structure includes fiber size, arrangement orientation and arrangement density, and the material properties include non-woven fabric material type and fluorescence efficiency; The preset non-woven fabric pre-generated image module is constructed by the following steps: The basic network structure generation module uses 3D modeling software to establish the basic network structure of non-woven fabrics based on the surface fiber design structure; Defect structure generation module, which uses 3D modeling software to select whether to insert defect structures into the basic network structure; Setting the application material and fluorescence efficiency parameters of the basic network structure in the three-dimensional modeling software according to the type of non-woven fabric material and the fluorescence efficiency; Add backlight source to the basic network structure; Changing the intensity of the backlight source and rendering the basic network structure using an optical rendering engine, and obtaining non-woven fabric rendering images under different backlight intensities by setting a virtual camera; Constructing an optical mask processing model, wherein the network framework of the optical mask processing model is a generative adversarial network, collecting multiple actual non-woven fabric images and corresponding non-woven fabric rendering images, using the actual non-woven fabric surface images as labels and the corresponding non-woven fabric rendering images as input, and training the generative adversarial network to obtain the optical mask processing model; The non-woven fabric rendering images under different backlight intensities are input into the optical mask processing model for processing to obtain pre-generated non-woven fabric images under different backlight intensities.

3. The nonwoven fabric defect detection method according to claim 1, wherein: The preset defect recognition model is trained through the following steps: The network framework of the defect recognition model is a convolutional neural network; A plurality of non-woven fabric defect images with different defect types are collected, and the plurality of non-woven fabric defect images are used as input and the defect type is used as a label to train a defect recognition model.

Images