Intelligent cashmere fabric inspection equipment

Abstract

The utility model relates to intelligent cashmere fabric inspection equipment. According to the scheme, the intelligent cashmere fabric inspection equipment comprises a rack, the supporting frame is mounted in the top area of the rack; the lifting module is installed on the supporting frame, connected with the horizontal module and used for driving the horizontal module to move up and down; the camera shooting group comprises a left camera shooting module, a middle camera shooting module and a right camera shooting module and is used for shooting the cashmere fabric on the inspection bench; the horizontal module is in driving connection with the left camera module and the right camera module; the inspection bench is located below the supporting frame, the top surface is made of a light-transmitting material, and a light source is arranged inside; the input mechanism is located below the supporting frame and arranged on the left side and the right side of the inspection table, and cashmere fabric is fixed through a clamp; and the man-machine interaction panel is in communication connection with the lifting module, the camera group, the horizontal module, the inspection bench and the input mechanism. The cashmere fabric can be rapidly and automatically detected, the detection efficiency is improved, and the detection cost is reduced.

Description

Technical Field

[0001] The utility model relates to a detection device, in particular to an intelligent inspection device for cashmere fabrics. Background Art

[0002] Before leaving the factory, cashmere fabrics need to be detected for defects such as broken threads. Currently, the most common method is to install them on a specific tooling and then observe them with the naked eye. For example, a wool and cashmere fabric inspection device disclosed in CN215493083U. This method not only has low detection efficiency, but also is prone to omissions. Moreover, once an error occurs, it is impossible to trace back and there is no way to conduct traceability.

[0003] Therefore, there is an urgent need for an intelligent inspection device for cashmere fabrics that can quickly detect cashmere fabrics and has the ability of traceability. Summary of the Utility Model

[0004] The purpose of the utility model is to provide an intelligent inspection device for cashmere fabrics in view of the above problems existing in the prior art.

[0005] To achieve the above application purpose, the utility model adopts the following technical solutions: An intelligent inspection device for cashmere fabrics includes:

[0006] A frame;

[0007] A support frame, installed in the top area of the frame;

[0008] A lifting module, installed on the support frame and connected to the horizontal module, for driving the horizontal module to move up and down;

[0009] A camera group, including a left camera module, a middle camera module and a right camera module, for photographing the cashmere fabric located on the inspection table;

[0010] A horizontal module, respectively drivingly connected to the left camera module and the right camera module, for driving the left camera module and the right camera module to move back and forth along the horizontal direction respectively;

[0011] An inspection table, located below the support frame, the top surface of which is made of a light-transmitting material and is provided with a light source inside;

[0012] An input mechanism, located below the support frame and arranged on the left and right sides of the inspection table, fixing the cashmere fabric through a clamp, for driving the cashmere fabric to move back and forth along the length direction of the inspection table;

[0013] A human-computer interaction panel, communicatively connected to the lifting module, the camera group, the horizontal module, the inspection table and the input mechanism.

[0014] Further, the middle camera module is fixed at the center of the horizontal module and is also located on the center line in the width direction of the inspection table.

[0015] Furthermore, the human-machine interaction panel is built with a label printer capable of printing qualified labels and unqualified labels.

[0016] Furthermore, the lifting module is a linear module, which is vertically connected to the support frame.

[0017] Furthermore, the horizontal module is also a linear module, and the left camera module and the right camera module correspond to one horizontal module respectively, the two horizontal modules are connected in a straight line, and the middle camera module is installed at the center of the two horizontal modules.

[0018] Furthermore, the input mechanism is a conveyor belt, and a plurality of clamps are arranged on the conveyor belt along a rotation path.

[0019] Furthermore, each camera module of the camera group has a resolution of at least 1080P, a frame rate of at least 60fps, an image sensor size of at least 1 inch, and an aperture of at least f / 1.8.

[0020] Furthermore, the protection level of each camera module of the camera group is at least IP65.

[0021] Furthermore, the positioning accuracy of the horizontal module is between ±0.02mm and ±0.05mm, the repeatability is no higher than ±0.01mm, the maximum speed is 50-200mm / s, and the acceleration is 0.5-1m / s 2 , load capacity 3-5kg, response time less than 100ms.

[0022] Furthermore, a flexible contact surface is provided on one side of the clamp that clamps the cashmere fabric.

[0023] Compared with the prior art, the cashmere fabric intelligent inspection equipment provided by the utility model significantly improves the quality control efficiency and accuracy of cashmere products through the following beneficial effects:

[0024] 1. Improved automation and intelligence: The integrated camera group and precise drive mechanism realize fully automatic and high-precision detection of cashmere fabrics, replacing the traditional manual visual inspection, significantly improving detection efficiency, reducing labor costs and human errors, and making the detection process more objective and accurate.

[0025] 2. All-round detection without omissions: The multi-camera module layout (left, middle and right camera modules) ensures that the fabric surface is fully covered. In particular, the center camera module is set in the center, which further enhances the ability to capture defects in the center area of ​​the fabric and avoids any potential blind spots.

[0026] 3. High-definition image acquisition: Each camera module is configured with at least 1080P resolution and a large aperture of f / 1.8. Combined with a high frame rate and a large-size image sensor, it can clearly record the details of the fabric even under complex lighting conditions, accurately identify defects such as broken threads, color differences, and impurities, improving the sensitivity and reliability of defect detection.

[0027] 4. Precise control and high stability: The precise positioning and control of the horizontal module and the lifting module ensure smooth movement at different detection heights and widths. The positioning accuracy of ±0.02mm to ±0.05mm and the repeat positioning accuracy of no more than ±0.01mm, combined with a fast response time, guarantee the continuity and stability of the detection process and reduce image blurring caused by equipment movement.

[0028] 5. Enhanced humanization and traceability: The human-machine interaction panel integrates a label printer to immediately print inspection result labels, which not only improves work efficiency but also realizes the immediate feedback of detection results and product traceability, facilitating subsequent quality management and responsibility tracing.

[0029] 6. Durable and highly adaptable: The IP65 protection level of the camera module and the flexible contact surface design of the fixture ensure good dust and waterproof performance of the equipment in the actual operating environment of the textile factory and gentle treatment of cashmere fabrics, extending the service life of the equipment and reducing maintenance costs.

[0030] 7. In summary, the intelligent inspection equipment for cashmere fabrics of the present utility model not only greatly improves the detection efficiency and accuracy but also provides strong technical support for the quality assurance of cashmere products through intelligent and humanized design concepts, meeting the requirements of the modern textile industry for high efficiency, precision, and sustainable development. Brief Description of the Drawings

[0031] Figure 1 is a schematic structural diagram of the present utility model;

[0032] Figure 2 is a schematic diagram of a scanning path of the camera group.

[0033] In the figure, 1, frame; 2, support frame; 3, lifting module; 4, horizontal module; 5, left camera module; 6, middle camera module; 7, right camera module; 8, inspection table; 9, input mechanism; 10, fixture; 11, human-machine interaction panel. Detailed Embodiment

[0034] The technical solutions in 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. Obviously, the described embodiments are only a part of the embodiments of the present utility model, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present utility model belong to the scope of protection of the present utility model.

[0035] Those skilled in the art should understand that in the disclosure of the present utility model, the orientation or positional relationships indicated by the terms "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present utility model and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the above terms should not be construed as limiting the present utility model.

[0036] Embodiment 1

[0037] As Figure 1-2 shown, this intelligent inspection equipment for cashmere fabrics includes:

[0038] Frame 1 and support structure: The main body of the equipment is built on a sturdy metal frame 1, and the frame 1 is designed to be modular for easy installation and maintenance. The support frame 2 is made of lightweight and high-strength aluminum alloy material and is firmly installed on the top of the frame 1 to ensure the stable support of the entire detection system.

[0039] Lifting module 3 and horizontal module 4: The lifting module 3 consists of a precision linear guide rail and a servo motor. Through precise control of the servo motor, the vertical up and down movement of the horizontal module 4 is realized, and the positioning accuracy reaches ±0.05 mm. The horizontal module 4 is also based on a high-precision linear guide rail, driving the left camera module 5 and the right camera module 7 to move horizontally along the inspection table 8. The horizontal movement accuracy is ±0.02 mm, the repeat positioning accuracy is ≤±0.01 mm, the maximum speed is controlled at 150 mm / s, and the acceleration is 0.75 m / s 2 , ensuring rapid and smooth coverage of the entire inspection area. The middle camera module 6 is fixed at the central intersection point of the two horizontal modules 4 to achieve detailed monitoring of the central area.

[0040] Camera group configuration: The camera group includes three high-resolution camera modules, each of which uses at least 1080P resolution, 60fps frame rate, 1-inch image sensor and f / 1.8 large aperture lens to ensure the capture of clear and delicate fabric images under various lighting conditions. The external packaging of the camera module meets the IP65 protection level, is dustproof and waterproof, and adapts to the working environment of a textile workshop. The specific identification of fabric defects is the use of existing technology, that is, the use of machine vision or deep learning to establish an identification module, which can quickly identify defects and record the image and coordinates of the defects. One method is as shown in Example 2 below.

[0041] Inspection table 8 and lighting: The surface of the inspection table 8 is paved with a transparent and wear-resistant acrylic plate, and has a built-in LED light source with adjustable brightness and color temperature to ensure uniform illumination of the fabric surface without shadow areas, which is conducive to defect identification.

[0042] Input mechanism 9 and clamps 10: The input mechanism 9 uses a high-quality conveyor belt, the surface of which is covered with antistatic material. Multiple sets of clamps 10 with flexible contact surfaces (rubber, silicone) are arranged along the rotation path. These clamps 10 can gently and firmly fix cashmere fabrics of different thicknesses to avoid pulling damage. The conveyor belt drive system controls the fabric to move smoothly on the inspection table 8, and the speed is adjustable in the range of 20-120m / min.

[0043] Human-machine interaction panel 11: The human-machine interaction panel 11 is integrated on one side of the device and adopts a touch screen design, which is intuitive and easy to operate. The embedded label printer in the panel can instantly print qualified or unqualified labels according to the test results, realizing rapid classification and quality traceability. In addition, the panel can display the test status, camera module field of view, test report and other information in real time, which is convenient for operators to monitor and adjust.

[0044] Example 2

[0045] This embodiment discloses the use of machine vision and deep learning technology to establish a recognition module to achieve rapid and accurate identification of fabric defects. The specific implementation steps are as follows:

[0046] 1. Data collection and preprocessing

[0047] Sample preparation: First, you need to collect a large number of different types of cashmere fabric samples, including defective and non-defective ones. The defect types include common problems such as broken threads, color difference, stains, and hair balls.

[0048] Image acquisition: Using the designed camera module system, the sample is photographed at high resolution from multiple angles (left, center, and right) to ensure clear images covering all potential defect areas.

[0049] Image preprocessing: Denoise, grayscale, enhance contrast, adjust brightness, etc. for the collected images to improve image quality and facilitate subsequent feature extraction.

[0050] 2. Feature extraction and annotation

[0051] Feature selection: Based on features such as texture, color, and shape of fabric images, extract defect features through traditional image processing methods (such as edge detection, morphological processing) or the feature extraction layers of deep learning networks (such as the early layers of convolutional neural network CNN).

[0052] Data annotation: Carefully annotate the preprocessed images, mark the specific positions and types of defects, and form a training set. This step can be completed manually by professionals or assisted by semi-automatic annotation tools.

[0053] 3. Deep learning model construction

[0054] Model selection and training: Based on a large amount of annotated image data, select a suitable deep learning model, such as convolutional neural network (CNN), recurrent neural network (RNN) combined with long short-term memory network (LSTM) for sequential image analysis, or more advanced models such as U-Net, Mask R-CNN, etc. for pixel-level segmentation and object detection.

[0055] Model training: Divide the annotated dataset into training set, validation set, and test set. Use the training set to train the model, the validation set to adjust model parameters, and the test set to evaluate model performance. During the training process, optimize the loss function (such as cross-entropy loss, Dice loss, etc.) to minimize the prediction error.

[0056] 4. Defect recognition and coordinate recording

[0057] Real-time recognition: Deploy the trained model to the human-machine interaction panel 11 of the device or the connected computing unit. When the camera module captures a new fabric image, immediately analyze it through the model to quickly identify whether there are defects.

[0058] Coordinate recording: Once the model recognizes a defect, use the feature map or bounding box information output by the model to record the exact position coordinates of the defect in the original image. This step is usually directly obtained through the output of the model. For example, in an object detection task, the model will output the class probability, bounding box position, etc. of each defect.

[0059] 5. Post-processing and report generation

[0060] Decision-making judgment: According to the recognition result and the preset threshold, judge whether the fabric is qualified. Record the defect type, position, etc. information of the unqualified fabric.

[0061] Image and Coordinate Recording: Store the image containing defects and the corresponding defect coordinates to provide a basis for subsequent analysis, re-inspection, or quality traceability.

[0062] Report Generation: The human-machine interaction panel 11 automatically collates the detection results and generates a detailed detection report, including information such as pass / fail labels, defect images, and position coordinates, and can be printed immediately through the built-in label printer.

[0063] Through the structural and functional design of the above embodiments, the intelligent inspection equipment for cashmere fabrics of the present utility model realizes an automated and highly accurate detection process, significantly improves the detection efficiency and accuracy, reduces the reliance on manpower and the misdetection rate, and is an ideal solution for modern textile quality control.

[0064] The parts not detailed in the present utility model are prior arts, so the present utility model does not elaborate on them.

[0065] It can be understood that the term "a" should be understood as "at least one" or "one or more". That is, in one embodiment, the number of an element can be one, while in other embodiments, the number of the element can be multiple. The term "a" cannot be understood as a limitation on the number.

[0066] Although terms such as the frame 1, the support frame 2, the lifting module 3, the horizontal module 4, the left camera module 5, the middle camera module 6, the right camera module 7, the inspection table 8, the input mechanism 9, the fixture 10, and the human-machine interaction panel 11 are used more in this article, the possibility of using other terms is not excluded. Using these terms is only to more conveniently describe and explain the essence of the present utility model; interpreting them as any additional limitation is contrary to the spirit of the present utility model.

[0067] The present utility model is not limited to the above best embodiment. Anyone can obtain other various forms of products under the inspiration of the present utility model. However, no matter what changes are made in its shape or structure, as long as there are technical solutions identical or similar to those of the present utility model, they all fall within the protection scope of the present utility model.

Claims

1. A cashmere fabric intelligent inspection device, characterized in that: include: frame; A support frame installed in the top area of ​​the rack; A lifting module is installed on the support frame and connected to the horizontal module to drive the horizontal module to move up and down; A camera group, including a left camera module, a middle camera module and a right camera module, for photographing the cashmere fabric on the inspection table; A horizontal module, connected to the left camera module and the right camera module, for driving the left camera module and the right camera module to move back and forth in a horizontal direction; An inspection table, located below the support frame, with a top surface made of light-transmitting material and a light source inside; An input mechanism, located below the support frame and disposed on the left and right sides of the inspection table, fixes the cashmere fabric through a clamp and is used to drive the cashmere fabric to move back and forth along the length direction of the inspection table; The human-machine interaction panel is communicatively connected with the lifting module, the camera group, the horizontal module, the inspection platform and the input mechanism.

2. The cashmere fabric intelligent inspection device according to claim 1, characterized in that: The middle camera module is fixed at the center of the horizontal module and is also located on the center line of the inspection table in the width direction.

3. The cashmere fabric intelligent inspection device according to claim 1, characterized in that: The human-machine interaction panel is built with a label printer capable of printing qualified labels and unqualified labels.

4. The cashmere fabric intelligent inspection device according to claim 1, characterized in that: The lifting module is a linear module and is vertically connected to the support frame.

5. The cashmere fabric intelligent inspection device according to claim 4, characterized in that: The horizontal module is also a linear module, and the left camera module and the right camera module correspond to one horizontal module respectively, the two horizontal modules are connected to form a straight line, and the middle camera module is installed at the center of the two horizontal modules.

6. The cashmere fabric intelligent inspection device according to claim 1, characterized in that: The input mechanism is a conveyor belt, on which a plurality of clamps are arranged along a rotation path.

7. The cashmere fabric intelligent inspection device according to claim 1, characterized in that: The resolution of each camera module of the camera group is at least 1080P, the frame rate is at least 60fps, the image sensor size is at least 1 inch, and the aperture is at least f / 1.

8.

8. The cashmere fabric intelligent inspection device according to any one of claims 1 to 7, characterized in that: The protection level of each camera module of the camera group is at least IP65.

9. The cashmere fabric intelligent inspection device according to any one of claims 1 to 7, characterized in that: The positioning accuracy of the horizontal module is between ±0.02mm and ±0.05mm, the repeatability is no higher than ±0.01mm, the maximum speed is 50-200mm / s, and the acceleration is 0.5-1m / s 2 , load capacity 3-5kg, response time less than 100ms.

10. The cashmere fabric intelligent inspection device according to any one of claims 1 to 7, characterized in that: A flexible contact surface is provided on one side of the clamp that clamps the cashmere fabric.

Images