A straight trough dipping system suitable for pultrusion process

Abstract

The present invention provides a straight trough type glue dipping system suitable for pultrusion process, comprising: a glue injection module for performing glue dipping operation on fibers; a detection module, which uses a camera device on the outside of the glue injection module to monitor and control the glue dipping quality of the glue injection module, uses a float sensing device on the inside of the glue injection module to control the working state of the glue injection module, and evaluates the glue dipping quality through a built-in visual recognition algorithm; wherein the camera device monitors the glue liquid level in real time and feeds back the rate of change of the liquid level, and adjusts the working parameters of the camera device according to the rate of change of the liquid level; an interactive module feeds back the evaluation results of the detection module to the client, and the staff adjusts various parameters in the glue dipping operation according to the evaluation results. Beneficial effects of the present invention: By combining the design of the camera device with the float sensing glue liquid level, the automated detection of production quality is completed, the work efficiency is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The invention belongs to the field of quality monitoring, and in particular relates to a straight trough type glue dipping system suitable for a pultrusion process. Background Art

[0002] Pultrusion is a process for producing composite material profiles by fully impregnating continuous fibers or fabrics with resin under traction equipment, then heating them through a molding die to solidify the resin. This molding method has the advantages of excellent longitudinal mechanical properties of the product, low manufacturing cost, high degree of automation, and stable product performance.

[0003] The main steps of the pultrusion process include yarn guiding, dipping, preforming, curing, pulling and cutting. Currently, the pultrusion process generally adopts an open roller dipping system, which has problems such as uneven fiber tension, poor fiber impregnation effect, and glue contamination, resulting in reduced product performance and poor straightness, affecting the application of pultruded profiles.

[0004] In the existing technology, problems such as fiber fuzzing, poor impregnation, uneven fiber tension, and glue contamination and waste are solved by closed low-pressure glue injection and the design of a reflow tank. However, unlike polyurethane, epoxy resin glue has a higher viscosity, and the closed dipping method has the problem of poor dipping. However, the closed glue tank cannot detect problems immediately, thus causing product defects. In addition, the use of manual methods to observe product problems consumes too much manpower. Summary of the Invention

[0005] In view of this, the present invention aims to propose a straight trough dipping system suitable for pultrusion process, in order to solve at least one of the above-mentioned technical problems.

[0006] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0007] A straight trough dipping system suitable for pultrusion process, comprising:

[0008] Glue injection module, used for dipping fibers in glue;

[0009] The detection module uses a camera device on the outside of the glue injection module to monitor and control the glue dipping quality of the glue injection module, uses a float sensing device on the inside of the glue injection module to control the working status of the glue injection module, and evaluates the glue dipping quality through a built-in visual recognition algorithm. The camera device monitors the glue liquid level in real time and provides feedback on the rate of change of the liquid level, and adjusts the operating parameters of the camera device according to the rate of change of the liquid level;

[0010] The interactive module feeds back the evaluation results of the detection module to the client, and the staff adjusts the various parameters in the dipping operation based on the evaluation results.

[0011] Furthermore, the glue injection module includes:

[0012] A straight-groove glue injection tank receives the fiber product at one end and is connected to a heatable cold mold at the other end via a sealing partition. The sealing cover of the straight-groove glue injection tank is a transparent structural member, and the sealing cover is connected to the straight-groove glue injection tank via a hinge.

[0013] Heatable cold die for heating the impregnated fibers using a heating plate.

[0014] Furthermore, the working process of the detection module includes:

[0015] The camera device captures images during the dipping operation in real time;

[0016] Performing preprocessing operations on the captured image, the preprocessing operations including median filtering denoising, adjusting brightness and contrast, and color space conversion;

[0017] The key features in the preprocessed image are extracted, and the unqualified areas in the image are divided according to the key features. The unqualified areas are compared with the preset quality standard map, and the evaluation results of the dipping quality are given according to the comparison.

[0018] Furthermore, the extraction of key features from the pre-processed image includes:

[0019] Extract the color characteristics of the colloid part, analyze the uniformity of the colloid distribution, and obtain the uniformity of the dipping;

[0020] Extract the structural characteristics of the fiber part, analyze whether the fiber is arranged neatly, whether there is dislocation and stacking, and obtain the fiber arrangement neatness;

[0021] The part of the image with significantly different brightness from the surrounding area is extracted, and the shape characteristics of the part are analyzed to obtain the bubble influence degree.

[0022] Furthermore, the analysis process of the dipping uniformity is as follows:

[0023] Convert the image from RGB color space to HSV color space;

[0024] Quantize the color value of each pixel and divide the color space into multiple discrete parts, each of which identifies a color range;

[0025] Perform color analysis on each part, calculate the frequency of occurrence of each color in each part, and analyze the uniformity of dipping based on the frequency of occurrence and the distribution of the color in each part.

[0026] Furthermore, the analysis process of the fiber arrangement regularity is as follows:

[0027] Quantify the grayscale of the image and compress it to a smaller range;

[0028] Preset a direction and distance to define the relative position of pixel pairs;

[0029] For each pair of pixels, if they are adjacent in the specified distance and direction, the value at the corresponding position is increased by 1, and the frequencies of all pixel pairs are stored in a matrix;

[0030] The texture features are extracted from the matrix to obtain the fiber alignment.

[0031] Furthermore, the analysis process of the bubble influence is as follows:

[0032] The image is binarized and divided into highlight areas and low-brightness areas according to the brightness difference. The number of pixels in the low-brightness area of ​​the current image is calculated to obtain the area of ​​the bubble part, and the bubble influence is calculated based on the area size.

[0033] Furthermore, the influence of the bubble is equal to the ratio of the area of ​​the bubble portion to the total area of ​​the non-background portion in the image.

[0034] Furthermore, the process of adjusting the working parameters of the camera device according to the liquid level change rate is specifically as follows:

[0035] When the floating change rate of the glue liquid level increases, the shutter time of the camera device is shortened and the aperture is reduced; when the floating change rate of the glue liquid level decreases, the shutter time is increased and the aperture is expanded.

[0036] Furthermore, a brightness threshold of the image is preset;

[0037] At the current shutter time, when the aperture is adjusted to the maximum value and the brightness of the image is still lower than the threshold, the sensitivity of the camera device is increased; otherwise, the sensitivity remains unchanged.

[0038] Compared with the prior art, the straight trough dipping system suitable for pultrusion process described in the present invention has the following beneficial effects:

[0039] The use of a transparent observable closing cover and a heatable cold mold facilitates the monitoring of production quality and increases production speed. At the same time, the design of a camera device combined with a float ball to sense the glue liquid level completes the automated detection of production quality, improves work efficiency and reduces labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 This is a schematic diagram of the structure and functions of a straight trough dipping system suitable for pultrusion process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0043] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are 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 cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0044] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0045] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0046] A straight trough dipping system suitable for pultrusion process, comprising:

[0047] Glue injection module, used for dipping fibers in glue;

[0048] The detection module uses a camera device on the outside of the glue injection module to monitor and control the glue injection quality of the glue injection module, and uses a float sensing device on the inside of the glue injection module to control the working status of the glue injection module (glue injection time, glue injection amount, glue injection speed). The glue injection quality is evaluated using a built-in visual recognition algorithm. The camera device monitors the glue liquid level in real time and provides feedback on the liquid level change rate, and the operating parameters of the camera device are adjusted according to the liquid level change rate.

[0049] The interactive module feeds back the evaluation results of the detection module to the client, and the staff adjusts the various parameters in the dipping operation based on the evaluation results.

[0050] The glue injection module includes:

[0051] A straight-groove glue injection tank receives the fiber product at one end and is connected to a heatable cold mold at the other end via a sealing partition. The sealing cover of the straight-groove glue injection tank is a transparent structural member, and the sealing cover is connected to the straight-groove glue injection tank via a hinge.

[0052] Heatable cold die for heating the impregnated fibers using a heating plate.

[0053] The working process of the detection module includes:

[0054] The camera device captures images during the dipping operation in real time;

[0055] Performing preprocessing operations on the captured image, the preprocessing operations including median filtering denoising, adjusting brightness and contrast, and color space conversion;

[0056] The key features in the preprocessed image are extracted, and the unqualified areas in the image are divided according to the key features. The unqualified areas are compared with the preset quality standard map, and the evaluation results of the dipping quality are given according to the comparison.

[0057] The key features extracted from the pre-processed image include:

[0058] Extract the color characteristics of the colloid part, analyze the uniformity of the colloid distribution, and obtain the uniformity of the dipping;

[0059] Extract the structural characteristics of the fiber part, analyze whether the fiber is arranged neatly, whether there is dislocation and stacking, and obtain the fiber arrangement neatness;

[0060] Extract the parts with different brightness in the image, analyze and determine whether the part is the bubble area, extract the shape characteristics of the bubble area, and obtain the bubble influence degree.

[0061] The analysis process of the dipping uniformity is as follows:

[0062] Convert the image from RGB color space to HSV color space;

[0063] Quantize the color value of each pixel and divide the color space into multiple discrete parts, each of which identifies a color range;

[0064] Perform color analysis on each part, calculate the frequency of occurrence of each color in each part, and analyze the uniformity of dipping based on the frequency of occurrence and the distribution of the color in each part.

[0065] The formula for calculating the frequency of occurrence of each color in each section is:

[0066] ;

[0067] Where I is the set of all pixels in the image, representing the input image; p(x,y) is the pixel at the (x,y) coordinate in the image. c(p(x,y)) is the color value of pixel p(x,y), which is specifically expressed as hue, saturation, and lightness in the HSV color space; H c (i) is the value of the i-th bin in the color histogram, indicating the frequency of the pixel with color value i in the image; δ(x) is the indicator function, which is 1 when x is true and 0 otherwise; N is the number of bins in the color channel.

[0068] In order to make the histogram unaffected by the image size, the normalized color histogram is:

[0069] ,in, is the normalized color histogram, which indicates the relative frequency of color value i in the image. It is the sum of all bins of the histogram, that is, the total number of all color pixels in the image.

[0070] The analysis process of the fiber arrangement regularity is as follows:

[0071] Quantify the grayscale of the image and compress it to a smaller range;

[0072] Preset a direction and distance to define the relative position of pixel pairs;

[0073] For each pair of pixels, if they are adjacent in the specified distance and direction, the value at the corresponding position is increased by 1, and the frequencies of all pixel pairs are stored in a matrix;

[0074] The texture features are extracted from the matrix to obtain the fiber alignment.

[0075] The definition formula of the matrix is:

[0076] P(i,j)=∑ x,y δ(I(x,y)=i,I(x+d,y+d)=j);

[0077] Where i and j are grayscale values, representing the grayscale values ​​of two pixels in the image; P(i,j) is an element in the co-occurrence matrix, indicating the frequency of occurrence of pixel pairs with grayscale values ​​i and j at a certain distance and direction; δ is an indicator function, which takes the value 1 when the condition is met and 0 otherwise; I(x,y) is the grayscale value of the pixel (x,y) in the image; d is the specified distance, usually 1; θ is the direction, and common angles include 0° (horizontal), 45°, 90° (vertical), and 135° (diagonal).

[0078] A variety of texture features can be extracted from the matrix, including:

[0079] A= ,

[0080] Where i and j are the grayscale values ​​in the co-occurrence matrix; P(i,j) is the co-occurrence frequency of the corresponding grayscale values ​​i and j;

[0081] The larger the value of A, the greater the grayscale difference of the image. If the value of A at a certain point in the image is too small, it means that the fibers are aggregated and stacked there, which is considered unqualified.

[0082] B= ,in;

[0083] μx and μy are the average grayscale values ​​of i and j respectively:

[0084] , ;

[0085] σx and σy are the standard deviations of i and j respectively:

[0086] , ;

[0087] The higher the B value, the more regular the grayscale changes in the image. If the B value at a certain point in the image is too low, it means that the fibers are arranged in a disorderly manner and are considered unqualified.

[0088] C= The larger the C value is, the smoother the texture of the image is and the smaller the grayscale change is. If the C value at a certain point in the image is too small, it means that the fiber is bent and curled at this point, which is considered unqualified.

[0089] In order to improve the detection efficiency and enable the staff to obtain more intuitive analysis results, the above three parameters A, B, and C are used for further calculation to obtain the value of fiber alignment. The specific process is as follows:

[0090] ;

[0091] ;

[0092] Among them, α1, α2, α3 are the weights of the first-order derivative of each characteristic, satisfying α1+α2+α3=1; β3 is the weight of the second-order derivative of uniformity, which is only when the liquid level change rate exceeds L threshold When it works; L threshold Liquid level change rate threshold.

[0093] The analysis process of the bubble influence is as follows:

[0094] The image is binarized and divided into highlight areas and low-brightness areas according to the brightness difference. The number of pixels in the low-brightness area of ​​the current image is calculated to obtain the area of ​​the bubble part, and the bubble influence is calculated based on the area size.

[0095] The formula for calculating the number of pixels in the low-light area is:

[0096] ;

[0097] Where δ(I(x,y)−1) is an indicator function that returns 1 when the value of pixel I(x,y) is 1 (i.e., a foreground pixel) and 0 otherwise. (x,y) is a pixel position in the image, and I(x,y) represents the grayscale value or binary value (0 or 1) of the pixel. ∑i,j represents the sum of all image pixels to calculate the total number of pixels in the foreground area.

[0098] The influence of the bubble is equal to the ratio of the area of ​​the bubble portion to the total area of ​​the non-background portion in the image.

[0099] The larger the bubble impact value, the more serious the impact of the bubbles on the resin layer. Usually, when the impact exceeds a certain threshold (such as 10% or 20%), the system will determine that the image quality is unqualified and requires further adjustment or repair.

[0100] The process of adjusting the working parameters of the camera device according to the liquid level change rate is specifically as follows:

[0101] When the floating change rate of the glue liquid level increases, the shutter time of the camera device is shortened and the aperture is reduced; when the floating change rate of the glue liquid level decreases, the shutter time is increased and the aperture is expanded.

[0102] Preset the brightness threshold of the image;

[0103] At the current shutter time, when the aperture is adjusted to the maximum value and the brightness of the image is still lower than the threshold, the sensitivity of the camera device is increased; otherwise, the sensitivity remains unchanged.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

[0105] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A straight trough dipping system suitable for pultrusion process, characterized in that: include: Glue injection module, used for dipping fibers in glue; The detection module uses a camera device on the outside of the glue injection module to monitor and control the glue dipping quality of the glue injection module, uses a float sensing device on the inside of the glue injection module to control the working status of the glue injection module, and evaluates the glue dipping quality through a built-in visual recognition algorithm. The camera device monitors the glue liquid level in real time and provides feedback on the rate of change of the liquid level, and adjusts the operating parameters of the camera device according to the rate of change of the liquid level; The interactive module feeds back the evaluation results of the detection module to the client, and the staff adjusts the various parameters in the dipping operation according to the evaluation results; The working process of the detection module includes: The camera device captures images during the dipping operation in real time; Performing preprocessing operations on the captured image, the preprocessing operations including median filtering denoising, adjusting brightness and contrast, and color space conversion; Extract key features from the pre-processed image, divide the unqualified area in the image according to the key features, compare it with the preset quality standard map, and give the evaluation result of the dipping quality based on the comparison; The key features extracted from the pre-processed image include: Extract the color characteristics of the colloid part, analyze the uniformity of the colloid distribution, and obtain the uniformity of the dipping; Extract the structural characteristics of the fiber part, analyze whether the fiber is arranged neatly, whether there is dislocation and stacking, and obtain the fiber arrangement neatness; Extract the part of the image with significantly different brightness from the surrounding area, analyze the shape characteristics of the part, and obtain the bubble influence degree; The analysis process of the fiber arrangement regularity is as follows: Quantify the grayscale of the image and compress it to a smaller range; Preset a direction and distance to define the relative position of pixel pairs; For each pair of pixels, if they are adjacent in the specified distance and direction, the value at the corresponding position is increased by 1, and the frequencies of all pixel pairs are stored in a matrix; Extract texture features from the matrix to obtain fiber alignment; Extract multiple texture features from the matrix, including: Grayscale difference of image A = ∑ i，j (ij) 2 P(i, j), Where i and j are the grayscale values ​​in the co-occurrence matrix; P(i,j) is the co-occurrence frequency of the corresponding grayscale values ​​i and j; Grayscale changes in the image in; μx and μy are the average grayscale values ​​of i and j respectively: μ x ∑ i i ·P(i,j),μ y ∑ j j·P(i,j): σx and σy are the standard deviations of i and j respectively: Image texture The three parameters A, B, and C are used to calculate the value of fiber alignment. The specific process is as follows: Among them, α1, α2, α3 are the weights of the first-order derivative of each characteristic, satisfying α1+α2+α3=1; β3 is the weight of the second-order derivative of uniformity, which is only when the liquid level change rate exceeds L threshold When it works; L threshold Liquid level change rate threshold.

2. A straight trough dipping system suitable for pultrusion process according to claim 1, characterized in that: The glue injection module includes: A straight-groove glue injection tank receives the fiber product at one end and is connected to a heatable cold mold at the other end via a sealing partition. The closure cover of the straight-groove glue injection tank is a transparent structural member, and the closure cover is connected to the straight-groove glue injection tank via a hinge. Heatable cold die for heating the impregnated fibers using a heating plate.

3. A straight trough dipping system suitable for pultrusion process according to claim 1, characterized in that: The analysis process of the dipping uniformity is as follows: Convert the image from RGB color space to HSV color space; Quantize the color value of each pixel and divide the color space into multiple discrete parts, each of which identifies a color range; Perform color analysis on each part, calculate the frequency of occurrence of each color in each part, and analyze the uniformity of dipping based on the frequency of occurrence and the distribution of the color in each part.

4. A straight trough dipping system suitable for pultrusion process according to claim 1, characterized in that: The analysis process of the bubble influence is as follows: The image is binarized and divided into high-brightness area and low-brightness area according to the brightness difference. The number of pixels in the low-brightness area of ​​the current image is calculated to obtain the area of ​​the bubble part, and the bubble influence is calculated based on the area size.

5. The straight trough dipping system suitable for pultrusion process according to claim 4, characterized in that: The influence of the bubble is equal to the ratio of the area of ​​the bubble portion to the total area of ​​the non-background portion in the image.

6. The straight trough dipping system suitable for pultrusion process according to claim 1, characterized in that: The process of adjusting the working parameters of the camera device according to the liquid level change rate is specifically as follows: When the floating change rate of the glue liquid level increases, the shutter time of the camera device is shortened and the aperture is reduced; when the floating change rate of the glue liquid level decreases, the shutter time is increased and the aperture is expanded.

7. A straight trough dipping system suitable for pultrusion process according to claim 6, characterized in that: Preset the brightness threshold of the image; At the current shutter time, when the aperture is adjusted to the maximum value and the brightness of the image is still lower than the threshold, the sensitivity of the camera device is increased; otherwise, the sensitivity remains unchanged.

Images