Fiber quality detection device and method based on array image acquisition unit

Abstract

The invention relates to a fiber quality detection device based on array image acquisition units. The fiber quality detection device comprises a plurality of image acquisition units, a switch and an industrial personal computer, the plurality of image acquisition units are arranged in a linear array along the width direction of the to-be-detected fiber, each image acquisition unit comprises an image sensor and a lens, and the adjacent lenses are overlapped in a scanning area of the to-be-detected fiber; the switch is electrically connected with the plurality of image sensors; and the industrial personal computer is electrically connected with the switch. The fiber quality detection device can completely cover the full width of the fiber to be detected, is wide in visual field range, high in scanning speed and low in omission ratio, and meanwhile, the relative speed with the fiber is smaller than that of a scanning scheme of a single image acquisition unit when the fiber quality detection device is used, so that a clearer image can be obtained to improve the impurity identification accuracy, and the detection accuracy is improved. And the detection accuracy is higher.

Description

Technical Field

[0001] The present invention belongs to the technical field of textile machinery, and particularly relates to a fiber quality detection device and method based on an array image acquisition unit. Background Art

[0002] In modern textile industry, the quality of fibers directly affects the performance of yarns and final textiles. Impurities in fibers (such as neps, cottonseed hulls, sand, branches and leaves, etc.) will cause a decrease in yarn strength, seriously affecting yarn quality and even causing equipment failures. Traditional detection methods rely on manual visual inspection or off-line sampling, which have defects such as low efficiency, poor real-time performance, and high missed detection rate. At present, there are also detection methods based on linear scanning of a single image acquisition unit (camera), but they are limited by scanning speed, resolution, field of view, etc., and are prone to missed detection problems, making it difficult to meet the requirements of high-speed and high-precision on-line fiber quality detection. Summary of the Invention

[0003] The main object of the present invention is to propose a fiber quality detection device and method based on an array image acquisition unit, which can effectively solve the problems in the background art.

[0004] To achieve the above object, the present invention is realized through the following technical solutions:

[0005] A fiber quality detection device based on an array image acquisition unit, comprising

[0006] A plurality of image acquisition units, arranged in a "one"-shaped array along the width direction of the fiber to be measured, the image acquisition unit includes an image sensor and a lens, and there is an overlap in the scanning areas of the adjacent lenses for the fiber to be measured;

[0007] A switch, electrically connected to the plurality of image sensors;

[0008] An industrial control computer, electrically connected to the switch.

[0009] Preferably, it further includes

[0010] A housing, having a glass window, the glass window facing the fiber to be measured, and the plurality of image acquisition units are installed in the housing.

[0011] Preferably, it further includes

[0012] Two linear array light sources, located in the housing, symmetrically arranged on both sides of the plurality of image acquisition units, and arranged obliquely, for illuminating the fiber to be measured through the glass window.

[0013] Preferably, the linear array light source is a linear array LED light source.

[0014] Preferably, the industrial control computer has a human-machine interface.

[0015] A fiber quality detection method based on an array image acquisition unit, using the fiber quality detection device described in any one of the above, includes the following steps:

[0016] Step S1: A number of lenses and image sensors collect real-time images of the fiber to be measured across the full width, transmit them to a switch for aggregation, and the switch transmits the aggregated images to an industrial control computer;

[0017] Step S2: The industrial control computer preprocesses the images by denoising, enhancing, and grayscaling;

[0018] Step S3: The industrial control computer, based on a deep learning neural network, identifies fiber impurities, marks the bounding boxes, and counts the types, quantities, and size information of the impurities;

[0019] Step S4: Finally, store the detection results in a database and display them in real time through a human-machine interface.

[0020] Preferably, step S4 further includes generating a quality trend report based on the detection results and supporting historical data backtracking and statistical analysis through the database.

[0021] The present invention provides a fiber quality detection device and method based on an array image acquisition unit, having the following beneficial effects:

[0022] 1. The fiber quality detection device of the present invention is provided with a number of image acquisition units, and the number of image acquisition units is arranged in a "one"-shaped array along the width direction of the fiber to be measured. The image acquisition unit includes an image sensor and a lens. There is an overlap in the scanning areas of adjacent lenses for the fiber to be measured, so that the full width of the fiber to be measured can be completely covered, with a wide field of view, fast scanning speed, and low missed detection rate.

[0023] 2. At the same time, for the fiber quality detection device of the present invention based on an array image acquisition unit, the relative speed with the fiber during use is less than the scanning scheme of a single image acquisition unit, so that clearer images can be obtained to improve the accuracy of impurity recognition, and the detection accuracy is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a side view of the fiber quality detection device of the present invention;

[0025] Figure 2 is a front view of the fiber quality detection device of the present invention;

[0026] Figure 3 is a top view of the fiber quality detection device of the present invention.

[0027] In the figure: 1. Outer shell; 2. Image sensor; 3. Lens; 4. Linear array light source; 5. Glass window; 6. Communication bus; 7. Fiber to be measured. Specific embodiments

[0028] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention.

[0029] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. 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 scope of protection of the present invention.

[0030] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention 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, and therefore should not be construed as a limitation of the present invention.

[0031] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined. In addition, the terms "installation", "connection" and "connection" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0032] Referring to Figures 1-3 , the present invention provides a fiber quality detection device based on an array image acquisition unit, including

[0033] A plurality of image acquisition units are arranged in a "one"-shaped array along the width direction of the fiber 7 to be measured. The image acquisition unit includes an image sensor 2 and a lens 3, and there is an overlap in the scanning areas of the adjacent lenses 3 for the fiber 7 to be measured;

[0034] A switch, electrically connected to the plurality of image sensors 2;

[0035] An industrial personal computer, electrically connected to the switch.

[0036] In this embodiment, the fibers to be detected are cotton fibers, wool fibers, chemical fibers, etc. The fiber quality detection device has a total of 19 image acquisition units, namely 19 image sensors 2 (2a to 2s) and 19 lenses 3 (3a to 3s). The image sensors 2, the switch and the industrial personal computer are connected through a communication bus 6.

[0037] In a specific implementation, it further includes

[0038] A housing 1, having a glass window 5, the glass window 5 facing the fiber 7 to be measured, and the plurality of image acquisition units are installed in the housing 1.

[0039] In a specific implementation, it further includes

[0040] Two linear array light sources 4, located in the housing 1, symmetrically arranged on both sides of the plurality of image acquisition units, arranged obliquely, for illuminating the fiber 7 to be measured through the glass window 5, so that the image acquisition units can acquire clear images. In this embodiment, the two linear array light sources 4 are 4a and 4b respectively.

[0041] In a specific implementation, the linear array light source 4 is a linear array LED light source.

[0042] In a specific implementation, the industrial personal computer has a human-machine interface.

[0043] The present invention also provides a fiber quality detection method based on an array image acquisition unit, using the above fiber quality detection device, including the following steps:

[0044] Step S1: A plurality of lenses 3 and image sensors 2 acquire real-time images of the fiber 7 to be measured in the full width, and transmit them to the switch for summarization. The switch transmits the summarized images to the industrial personal computer;

[0045] Step S2: The industrial personal computer performs preprocessing on the images, including noise reduction, enhancement and grayscale conversion;

[0046] Step S3: The industrial personal computer, based on a deep learning neural network, identifies fiber impurities, marks the bounding boxes and counts the types, quantities and size information of the impurities;

[0047] Step S4: Finally, the detection results are stored in the database and displayed in real time through the human-machine interface.

[0048] In a specific embodiment, the step S4 further includes generating a quality trend report according to the detection results and supporting historical data backtracking and statistical analysis through a database.

[0049] The fiber quality detection device of the present invention is provided with a plurality of image acquisition units. The plurality of image acquisition units are arranged in a "one"-shaped array along the width direction of the fiber 7 to be detected. The image acquisition unit includes an image sensor 2 and a lens 3. The scanning areas of adjacent lenses 3 for the fiber 7 to be detected overlap, so that the entire width of the fiber 7 to be detected can be completely covered, with a wide field of view, fast scanning speed and low missed detection rate.

[0050] At the same time, for the fiber quality detection device based on the array image acquisition unit of the present invention, the relative speed with the fiber during use should be less than the scanning scheme of a single image acquisition unit, so that clearer images can be obtained to improve the accuracy of impurity recognition and the detection accuracy is higher.

[0051] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A fiber quality detection device based on an array image acquisition unit, characterized in that: including a plurality of image acquisition units arranged in a "one"-shaped array along the width direction of the fiber to be measured. The image acquisition unit includes an image sensor and a lens, and there is an overlap in the scanning area of the adjacent lenses for the fiber to be measured; a switch electrically connected to the plurality of image sensors; an industrial control computer electrically connected to the switch.

2. The fiber quality detection device based on an array image acquisition unit according to claim 1, characterized in that: It further includes a housing with a glass window facing the fiber to be measured, and the plurality of image acquisition units are installed in the housing.

3. The fiber quality detection device based on an array image acquisition unit according to claim 2, wherein: It further includes two linear array light sources located in the housing, symmetrically arranged on both sides of the plurality of image acquisition units and inclined, for illuminating the fiber to be measured through the glass window.

4. The fiber quality detection device based on an array image acquisition unit according to claim 3, characterized in that: The linear array light source is a linear array LED light source.

5. The fiber quality detection device based on an array image acquisition unit according to claim 1, wherein: The industrial control computer is provided with a human-machine interface.

6. A fiber quality detection method based on an array image acquisition unit, which uses the fiber quality detection device according to any one of claims 1-5, characterized in that, It includes the following steps: Step S1: A plurality of lenses and image sensors acquire real-time images of the fiber to be measured in the full width, and transmit them to the switch for summarization. The switch transmits the summarized images to the industrial control computer; Step S2: The industrial control computer preprocesses the images by noise reduction, enhancement and grayscale conversion; Step S3: The industrial control computer identifies fiber impurities based on a deep learning neural network, marks the bounding boxes and counts the types, quantities and size information of the impurities; Step S4: Finally, the detection results are stored in the database and displayed in real time through the human-machine interface.

7. A fiber quality detection method based on an array image acquisition unit according to claim 6, characterized in that: Step S4 further includes generating a quality trend report according to the detection results, and supporting historical data backtracking and statistical analysis through the database.

Images