CN219348605U

CN219348605U - A fabric defect detection device

Info

Publication number: CN219348605U
Application number: CN202221290439.9U
Authority: CN
Inventors: 章永鉴; 韩军; 孔祥松; 耿鹏程; 杜宝昌
Original assignee: Xiamen University of Technology
Current assignee: Xiamen University of Technology
Priority date: 2022-05-27
Filing date: 2022-05-27
Publication date: 2023-07-14
Anticipated expiration: 2032-05-27

Abstract

The utility model provides a fabric defect detection device, which includes a workbench, a bracket assembly, a light source, a line array camera and a host; the workbench forms a table for placing fabrics, and the bracket assembly is connected to the At both ends of the workbench, a first crossbar is erected between the longitudinal bars; the line camera is fixed on the first crossbar, and can slide along the first crossbar, and can Adjusting the angle along the direction perpendicular to the first cross bar; the light source is a strip-shaped light source, which is fixed on the vertical bar parallel to the cross bar and located below the line camera, In addition, the light-emitting surface of the light source can be flipped along the direction of the vertical rod. This solution controls the light emitted by the light source to reflect back to the line-scan camera by adjusting the irradiation direction of the light-emitting surface of the light source and the shooting angle of the line-scan camera. , to maximize the amount of incoming light and take clearer pictures.

Description

Fabric flaw detection device

Technical Field

The utility model relates to the technical field of visual detection, in particular to a fabric flaw detection device.

Background

With the development of mechanical manufacturing technology, textile machines are widely applied to textile industry, and have high efficiency, large yield and stable performance, but in the production process, problems such as needle leakage, hole breakage, dirt, yarn hooking, warp breakage, weft missing and the like are inevitably generated due to raw materials or equipment, the detection of defects of traditional textiles is mainly carried out by human eyes for identification, the detection efficiency is low, human eyes are tired easily due to long-time observation, and the problem of missed detection is caused.

At present, with the development of visual detection technology, more and more manufacturers choose to adopt equipment based on visual detection to detect fabric flaws, and the flaws of fabrics are identified by collecting surface images of fabrics and combining an image identification technology.

However, since the color, material, etc. of different fabrics are greatly different, how to obtain a high-definition fabric surface image relates to the accuracy of flaw detection, and no related study exists at present.

Disclosure of Invention

Accordingly, an object of the present utility model is to provide a fabric defect detecting device, which solves the above-mentioned problems.

The utility model adopts the following scheme:

the application provides a fabric flaw detection device, which comprises a workbench, a bracket assembly, an image acquisition device and a host;

the workbench is provided with a table top for placing fabrics, the bracket component is connected to two ends of the table top of the workbench through two longitudinal rods, and a first transverse rod is erected between the longitudinal rods;

the image acquisition device comprises a light source and a linear array camera, wherein the linear array camera is fixed on the first cross rod, can slide along the first cross rod and can adjust an angle along a direction perpendicular to the first cross rod;

the light source is a strip-shaped luminous light source, is fixed on the longitudinal rod in parallel with the transverse rod and is positioned below the linear array camera, and the luminous surface of the light source can be turned over along the direction of the longitudinal rod.

Preferably, the light source is a dot matrix LED light source, and the CRI value of the LED light source is above 80.

Preferably, the light source is electrically connected with the host, and is configured to be controlled to be turned on and off and luminous flux by the host.

Preferably, the workbench and the bracket component are made of aluminum alloy materials.

Preferably, the bottom of the workbench is also provided with 4 universal pulleys and a fixing device.

Preferably, the host is further electrically connected with a display.

Preferably, the fabric flaw detection device can control the opening and closing of the braiding machine and the cloth winding machine through the host machine.

Preferably, the fabric defect detection device further comprises a laser marking device and a second cross bar, the second cross bar is arranged on the first cross bar, the laser marking device is arranged on the second cross bar and is configured to detect defects in the fabric defect detection device, and the position of the defects is marked on the fabric when the host machine closes the knitting machine and the cloth winding machine.

As a further improvement of the process,

by adopting the technical scheme, the utility model can obtain the following technical effects:

the support assembly is provided with the light source with the turnover luminous surface and the linear array camera with the adjustable shooting angle, and the light source is controlled to irradiate the light reflection linear array camera by adjusting the irradiation direction of the luminous surface of the light source and the shooting angle of the linear array camera, so that the light incoming quantity is improved to the maximum extent, and a clearer picture is shot.

Other features of the present utility model will become apparent from the following description of exemplary embodiments (with reference to the accompanying drawings).

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present utility model, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some examples of the present utility model and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an embodiment of the present utility model;

FIG. 2 is a flow chart of a deep learning predictive model in accordance with an embodiment of the utility model;

the drawings are as follows:

light source 100, linear camera 200, host 300, display 400, workstation 500, stand assembly 600, vertical rod 610, first rail 620, second rail 630, universal pulley 700

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present utility model more apparent, the technical solutions of the embodiments of the present utility model will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present utility model, and it is apparent that the described embodiments are some embodiments of the present utility model, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present utility model without making any inventive effort, are intended to fall within the scope of the present utility model. Thus, the following detailed description of the embodiments of the utility model, as presented in the figures, is not intended to limit the scope of the utility model, as claimed, but is merely representative of selected embodiments of the utility model. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present utility model without making any inventive effort, are intended to fall within the scope of the present utility model.

In the description of the present utility model, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present utility model and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present utility model.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present utility model, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the present utility model, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present utility model can be understood by those of ordinary skill in the art according to the specific circumstances.

In the present utility model, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above," "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature includes the first feature being directly under and obliquely below the second feature, or simply means that the first feature is less level than the second feature.

Examples

Referring to fig. 1 and 2, a first embodiment of the present utility model provides a fabric defect detecting device, which includes a workbench 500, a bracket assembly 600, an image capturing device, and a host 300;

the workbench 500 is formed with a table top for placing fabrics, the bracket assembly 600 is connected to two ends of the table top of the workbench 500 through two longitudinal rods 610, and a first cross rod 620 is erected between the longitudinal rods 610;

the image acquisition device comprises a light source 100 and a line camera 200, wherein the line camera 200 is fixed on the first cross bar 620, can slide along the first cross bar 620, and can adjust an angle along a direction perpendicular to the first cross bar 620;

the light source 100 is a strip-shaped light source 100, which is parallel to the cross bar, is fixed on the vertical bar 610, is positioned below the line camera 200, and the light emitting surface of the light source 100 can be freely turned over.

In this embodiment, the light source 100 is a dot matrix LED light source, and the CRI value of the LED light source is 85, which is not only small in size, low in energy consumption, energy-saving and environment-friendly, but also high in color reduction degree, and can detect the color difference of the textile more easily, and of course, the CRI value in other embodiments may be 90, 91 or even higher, and the utility model is not limited herein specifically.

In this embodiment, the light source 100 is electrically connected to the host 300, and is configured to control the on/off and luminous flux of the host 300, so that the host 300 can adjust the luminous flux of the light source 100 to achieve the best shooting light under the condition that the light difference between different factory line working environments is large, so that the line camera 200 can shoot the best picture.

In this embodiment, four universal pulleys 700 are further disposed at the bottom of the workbench 500, and a fixing device is disposed on the bottom of the workbench, the universal pulleys 700 enable the whole detection device to be used in a plurality of production lines in a fast moving manner, and after moving, the whole detection device can be fast fixed through the fixing device, so that the device is convenient and fast.

In this embodiment, the host 300 is further electrically connected to a display 400, and the host 300 is provided with corresponding detection software, where the display 400 is used to display the whole operation interface of the detection software, the photograph taken by the line camera 200, and information on the host 300;

the detection software is provided with a deep learning prediction model, the deep learning prediction model is used for shooting a defect picture on site, after image cutting, selection and data enhancement, a data set is established, the data set is divided into a training data set and a test data set, the training set is used for training the deep learning model, the test set is used for detecting the effect of the trained deep learning model, the deep learning prediction model is finally obtained through training, the model is used for detecting defects in the actual production process, full-automatic and efficient detection is achieved, and the deep learning prediction model and the training method thereof are all conventional common knowledge and are not described in detail herein.

The above is provided with the light source 100 with the reversible light emitting surface and the line camera 200 with the adjustable photographing angle on the bracket assembly 600, the light source 100 is controlled to irradiate the light reflection line camera 200 by adjusting the irradiation direction of the light emitting surface of the light source 100 and the photographing angle of the line camera 200, so as to maximally improve the light incoming quantity, photograph a clearer picture, then compare the photographed picture with the deep learning prediction model, and display the compared result on the display 400, so as to remind workers to timely process, realize full-automatic and high-efficiency detection, and meanwhile, 4 universal pulleys are arranged at the bottom of the workbench 500, so that the whole device can be used in a plurality of production lines.

Preferably, the workbench 500 and the bracket assembly 600 are made of aluminum alloy materials, and the aluminum alloy materials have smaller density and lighter weight, so that the bracket can move more conveniently.

Some preferred embodiments of the utility model are described further below.

On the basis of the first embodiment, in the second embodiment of the present utility model, the fabric defect detecting device may control the on/off of the knitting machine and the cloth winding machine through the host 300, when the fabric defect detecting device detects a defect on the fabric, not only the position of the defect is displayed on the display 400, but also the host 300 will automatically stop the operation of the knitting machine and the cloth winding machine, so as to avoid that the textile machine continues to work under the condition that the fabric has defects, such as needle leakage, hole breakage, warp breakage and weft missing, and the textile product is bad, even the raw material is lost due to the fact that the machine is not stopped in time.

Preferably, the fabric defect detecting device further comprises a laser marking device and a second cross bar 630, the second cross bar 630 is arranged on the first cross bar 620, the laser marking device is arranged on the second cross bar 630 and is configured to detect a defect by the fabric defect detecting device, and the position of the defect is marked on the fabric when the host 300 closes the knitting machine and the cloth winding machine, so that a worker can check the condition of the defect more quickly, the rapid processing is convenient, and the working efficiency is improved.

The above is only a preferred embodiment of the present utility model, and the protection scope of the present utility model is not limited to the above examples, and all technical solutions belonging to the concept of the present utility model belong to the protection scope of the present utility model.

Claims

1. The fabric flaw detection device is characterized by comprising a workbench, a bracket assembly, an image acquisition device and a host;

2. The fabric defect detection device of claim 1, wherein the light source is a dot matrix LED light source and the CRI value of the LED light source is 80 or more.

3. The fabric defect detection device of claim 1 wherein the light source is electrically connected to the host computer and configured to be controllable by the host computer for opening and closing and light flux.

4. The fabric defect detection device of claim 1, wherein the table and bracket assembly is an aluminum alloy material.

5. The fabric defect detection device of claim 1, wherein the table bottom is further provided with 4 universal pulleys and a fixing device.

6. The fabric defect detection device of claim 1, wherein the host is further electrically connected to a display.

7. The fabric defect detection device according to claim 1, wherein the fabric defect detection device can control the opening and closing of the knitting machine and the cloth winding machine through the host machine.

8. The fabric defect detection device of claim 7, further comprising a laser marking device and a second cross bar, the second cross bar being disposed on the first cross bar, the laser marking device being disposed on the second cross bar and configured to mark a location of a defect on the fabric when the fabric defect detection device detects the defect and the host machine shuts down the knitting machine and the fabric winder.