Monitoring method of long glass fiber reinforced plastic impregnation effect based on machine vision

Abstract

The present invention relates to the technical field of monitoring the wetting effect, and in particular to a monitoring method for the wetting effect of long glass fiber reinforced plastics based on machine vision, comprising: obtaining a plurality of image information of a glass fiber bundle; determining an arrangement evaluation value based on the image information to determine the wetting mode of the glass fiber bundle and the monitoring frequency of the wetting effect; obtaining a cross-sectional image of the long glass fiber reinforced plastic under the determined wetting mode and monitoring frequency, and dividing it into a plurality of regions; determining the grayscale average value corresponding to each region to establish an average value polyline, and determining the qualification of the wetting effect based on the fitting degree of the average value polyline; for unqualified wetting effects, statistically analyzing the proportion of glass fiber filaments with unqualified coating properties, and determining to adjust the traction speed based on the proportion of the number, or adjusting the wetting temperature / wetting pressure. The present invention improves the production quality of glass fiber reinforced plastics by monitoring the wetting effect.

Description

Technical Field

[0001] The invention relates to the technical field of glass fiber impregnation effect monitoring, and in particular to a machine vision-based method for monitoring the impregnation effect of long glass fiber reinforced plastics. Background Art

[0002] Machine vision is to use machines to replace human eyes to make measurements and judgments. The captured target is converted into an image signal through an image capture device, and then transmitted to a dedicated image processing system to obtain the morphological information of the captured target. This information will be converted into digital signals based on pixel distribution, brightness, color, etc., and then the equipment action on site will be controlled based on the judgment results. In large-scale repetitive industrial production processes, machine vision detection methods can greatly improve production efficiency and automation.

[0003] Long glass fiber reinforced plastic is a composite material with excellent performance, which is composed of long glass fiber and plastic matrix. Due to its high strength, high modulus, good heat resistance and corrosion resistance, long fiber reinforced thermoplastic materials (LFT) are widely used in automobiles, aerospace, electronics and other fields. In these applications, the wetting effect of glass fiber and plastic matrix directly affects the mechanical properties and overall quality of the composite material. Poor wetting will lead to a decrease in the interfacial bonding force between glass fiber and plastic matrix, thus affecting the strength and durability of the composite material.

[0004] Traditional methods for detecting the wetting effect mostly rely on manual observation and physical testing, which have the disadvantages of strong subjectivity, low efficiency, and difficulty in covering all products. The monitoring method based on machine vision can overcome these disadvantages and achieve rapid, accurate, and comprehensive detection of the wetting effect of long glass fiber reinforced plastics. Through image acquisition and processing, the wetting state of glass fiber in the plastic matrix can be obtained in real time, and problems such as poor wetting can be discovered in time, providing strong support for the optimization of the production process and quality control.

[0005] Chinese patent application publication number: CN101659091A discloses a production equipment of glass fiber reinforced plastic material, including a glass fiber preheating device, a glass fiber surface treatment device and a twin-screw extruder, wherein the glass fiber preheating device is transitionally connected with the glass fiber surface treatment device, and the glass fiber surface treatment device is transitionally connected with the twin-screw extruder. When used, the glass fiber first passes through a glass fiber preheating device composed of a group of heating elements to dry and loosen the stranded glass fiber; the preheated glass fiber then enters the glass fiber surface treatment device, and the prepared liquid coupling agent passes through the surface treatment agent atomization device to fully infiltrate the glass fiber surface, and the liquid coupling agent and the glass fiber surface are fully in contact to obtain a good treatment effect; the preheated and surface-treated glass fiber is pulled into the twin-screw extruder, mixed with the molten plastic, and cooled and pelletized after extrusion to obtain the glass fiber reinforced plastic material. The produced material has good comprehensive performance and is worthy of wide promotion and application in the industry.

[0006] It can be seen that the production equipment of the glass fiber reinforced plastic material has the following problems: the equipment lacks real-time monitoring of the production process of the glass fiber reinforced plastic and cannot determine the wetting effect of the glass fiber and the reinforced plastic, which leads to poor mechanical properties of the glass fiber reinforced plastic. Summary of the invention

[0007] To this end, the present invention provides a method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision, so as to overcome the problem that the mechanical properties of long glass fiber reinforced plastics are poor due to the lack of real-time monitoring of the wetting effect of long glass fiber reinforced plastics in the prior art.

[0008] To achieve the above object, the present invention provides a method for monitoring the wetting effect of long glass fiber reinforced plastic based on machine vision, comprising:

[0009] Acquire some image information of the pre-processed glass fiber bundle;

[0010] Determining an arrangement evaluation value of the glass fiber filaments based on the image information, and determining a wetting mode of the glass fiber bundle and a monitoring frequency of the wetting effect based on the arrangement evaluation value;

[0011] Under the determined infiltration mode and monitoring frequency, the long glass fiber reinforced plastic is subjected to a tensile test to obtain a cross-sectional image and the cross-sectional image is preprocessed, and a plurality of regions are divided with the center point of the cross section of the long glass fiber reinforced plastic as a reference point;

[0012] Determine a plurality of grayscale average values ​​corresponding to each of the regions, establish an average value polyline based on each of the grayscale average values, and determine the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fit of the average value polyline;

[0013] For unqualified wetting effects, the interface spacing between any glass fiber and the reinforced plastic is determined based on the cross-sectional image, whether the coating of a single glass fiber is qualified is determined based on the interface spacing, and the number ratio of glass fiber with unqualified coating is counted, so as to determine whether to adjust the pulling speed of the glass fiber bundle based on the number ratio, or adjust the wetting temperature / wetting pressure of the glass fiber reinforced plastic extrusion process.

[0014] Further, the process of determining the wetting mode of the glass fiber bundle based on the arrangement evaluation value includes:

[0015] comparing the arrangement evaluation value with a preset arrangement evaluation value;

[0016] Based on the comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value, determining that the infiltration mode is a first infiltration mode in which the ultrasonic device is turned on for infiltration;

[0017] Based on the comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value, the infiltration mode is determined to be a second infiltration mode in which the ultrasonic device is not turned on for infiltration.

[0018] Further, the process of determining the monitoring mode of the wetting effect of the glass fiber bundle based on the arrangement evaluation value includes:

[0019] comparing the arrangement evaluation value with a preset arrangement evaluation value;

[0020] Determining to perform monitoring in a first monitoring cycle based on a comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value;

[0021] Based on the comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value, it is determined to perform monitoring in the second monitoring cycle.

[0022] Furthermore, the process of establishing a mean value polyline based on each of the grayscale mean values ​​includes:

[0023] Determine the center point of the long glass fiber reinforced plastic section;

[0024] Divide the circle into several areas with the central point as the center and several preset distances as the radius;

[0025] Marking each of the regions in a direction extending from the edge of the cross-sectional image to the center of the circle;

[0026] An average value polyline is established with each of the regions as the horizontal coordinate and each of the grayscale average values ​​as the vertical coordinate.

[0027] Furthermore, the process of determining the degree of fit of the mean value polyline includes:

[0028] Determine a plurality of slope differences between corresponding positions of the mean value broken line and the standard broken line;

[0029] comparing the slope difference with a preset difference;

[0030] Determining that the slope of the average value polyline is qualified based on a comparison result that the slope difference is less than or equal to the preset difference;

[0031] The percentage of qualified slopes was counted and determined as the goodness of fit.

[0032] Further, the process of determining the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fitting degree of the average value polyline includes:

[0033] comparing the fitness with a preset fitness;

[0034] Based on the comparison result that the degree of fit is less than the preset degree of fit, it is determined that the infiltration effect is unqualified.

[0035] Further, the process of determining whether the coating property of a single glass fiber is qualified based on the interface spacing includes:

[0036] comparing the interface spacing with a preset spacing;

[0037] Based on the comparison result that the interface spacing is greater than the preset spacing, it is determined that the coating property of the single glass fiber is unqualified.

[0038] Furthermore, the process of determining the adjustment parameter based on the quantity proportion includes:

[0039] Comparing the quantity ratio with a preset ratio;

[0040] Determining to reduce the pulling speed of the glass fiber bundle based on a comparison result that the quantity ratio is greater than the preset ratio;

[0041] Based on the comparison result that the quantity proportion is less than or equal to the preset proportion, it is determined to increase the wetting temperature or the wetting pressure in the glass fiber reinforced plastic extrusion process.

[0042] Further, under the condition of determining to reduce the traction speed, the quantity proportion is subtracted from the preset proportion to obtain a first proportion difference, and based on a comparison result that the first proportion difference is greater than a first preset proportion difference, it is determined to reduce the traction speed by a first speed adjustment coefficient;

[0043] Based on a comparison result that the first proportion difference is less than or equal to the first preset proportion difference, it is determined to reduce the traction speed by a second speed adjustment coefficient.

[0044] Further, under the condition of determining to adjust the extrusion process, the preset proportion is subtracted from the quantity proportion to obtain a second proportion difference, and based on a comparison result that the second proportion difference is greater than the second preset proportion difference, it is determined to increase the infiltration temperature by the temperature adjustment coefficient;

[0045] Based on the comparison result that the second proportion difference is less than or equal to the second preset proportion difference, it is determined to increase the infiltration pressure by the pressure adjustment coefficient.

[0046] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention obtains high-definition images by utilizing machine vision, determines the arrangement evaluation value of the glass fiber according to the image information, and evaluates the arrangement orderliness of the glass fiber. The stronger the arrangement orderliness, the better the wetting effect. The subsequent wetting mode and the monitoring frequency of the wetting effect are determined based on the arrangement evaluation value, thereby improving the monitoring efficiency while ensuring the production quality. Under the determined wetting mode and monitoring frequency, the produced long glass fiber reinforced plastic is subjected to a tensile test, a cross-sectional image is obtained, the cross-sectional image is divided into regions and the grayscale average value of each region is determined, an average value polyline is established, the acceptability of the wetting effect is determined based on the fit of the average value polyline, and for the unqualified wetting effect, it is determined whether the coating property of a single glass fiber is qualified, and the production process of the long glass fiber reinforced plastic is adjusted based on the proportion of the unqualified number, thereby improving the mechanical properties of the long glass fiber reinforced plastic.

[0047] Furthermore, the present invention calculates the arrangement evaluation value based on the image features of the acquired glass fiber bundle. The glass fiber filaments in the glass fiber bundle may be entangled, crossed, and agglomerated. The more entangled, crossed, and agglomerated the phenomena are, the worse the impregnation effect is. The monitoring frequency of the glass fiber reinforced plastic needs to be increased accordingly to ensure the production quality, and the ultrasonic device is turned on to perform ultrasonic vibration on the impregnation process, thereby further improving the mechanical properties of the long glass fiber reinforced plastic.

[0048] Furthermore, in the present invention, the qualification of the wetting effect is determined according to the average value broken line. The cross-section of the long glass fiber reinforced plastic with good wetting effect becomes dark on the fracture surface and has a small grayscale value because the material absorbs a large amount of energy during the fracture process; the cross-section of the long glass fiber reinforced plastic with poor wetting effect has weak points or stress concentration areas in the material during the fracture process. These areas have low bearing capacity due to the poor wetting effect of the glass fiber, and there is no energy absorption process before fracture, which causes the cross-section to become bright and have a large grayscale value; from the overall situation of the entire cross-section, it can be seen that the fracture is from the edge to the middle, resulting in the most energy absorbed by the center of the material and the smallest grayscale value. The cross-section is divided into regions, and the grayscale average value corresponding to each region is determined to establish an average value broken line, which is compared with the standard broken line. The change in the grayscale average value is determined according to the slope of the corresponding position, which can characterize the cross-section condition of the long glass fiber reinforced plastic, and the wetting effect is expressed according to the cross-section condition, thereby improving the monitoring accuracy of the wetting effect and further improving the mechanical properties of the long glass fiber reinforced plastic.

[0049] Furthermore, the present invention determines whether the coating property of a single glass fiber is qualified by the interface distance between the glass fiber and the plastic. The larger the interface distance between the glass fiber and the plastic, the worse the wetting effect. The production process of the long glass fiber reinforced plastic is adjusted according to the value of the interface distance. The longer the pulling speed, the higher the wetting temperature, and the greater the wetting pressure, the better the wetting effect. However, too high parameters will lead to excessive energy consumption. Adjustment based on the interface distance can further improve the mechanical properties of the long glass fiber reinforced plastic while reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to an embodiment of the present invention;

[0051] Figure 2 A flow chart for determining a wetting pattern of a glass fiber bundle according to an embodiment of the present invention;

[0052] Figure 3 A flow chart for determining whether the infiltration effect is qualified according to an embodiment of the present invention;

[0053] Figure 4 The present invention is a flowchart for determining whether the coating property of a single glass fiber is qualified. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0056] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0057] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] See also Figure 1 - Figure 4 As shown, Figure 1 This is a flow chart of a method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to an embodiment of the present invention; Figure 2 A flow chart for determining a wetting pattern of a glass fiber bundle according to an embodiment of the present invention; Figure 3 A flow chart for determining whether the infiltration effect is qualified according to an embodiment of the present invention; Figure 4 The present invention is a flowchart for determining whether the coating property of a single glass fiber is qualified.

[0059] The embodiment of the present invention provides a method for monitoring the wetting effect of long glass fiber reinforced plastic based on machine vision, which is characterized by comprising:

[0060] Step S1, obtaining some image information of the pre-processed glass fiber bundle;

[0061] Step S2, determining an arrangement evaluation value of the glass fiber filaments based on the image information, and determining a wetting mode of the glass fiber bundle and a monitoring frequency of the wetting effect based on the arrangement evaluation value;

[0062] Step S3, under the determined infiltration mode and monitoring frequency, performing a tensile test on the long glass fiber reinforced plastic to obtain a cross-sectional image and preprocessing the cross-sectional image, dividing the cross-sectional image into a plurality of regions with the center point of the cross section of the long glass fiber reinforced plastic as a reference point;

[0063] Step S4, determining a plurality of grayscale average values ​​corresponding to each of the regions, establishing an average value polyline based on each of the grayscale average values, and determining the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fit of the average value polyline;

[0064] Step S5, for unqualified wetting effects, determine the interface spacing between any glass fiber and the reinforced plastic based on the cross-sectional image, determine whether the coating of a single glass fiber is qualified based on the interface spacing, and count the percentage of glass fibers with unqualified coating, so as to determine to adjust the pulling speed of the glass fiber bundle based on the percentage, or adjust the wetting temperature / wetting pressure of the glass fiber reinforced plastic extrusion process.

[0065] Specifically, the pretreatment of the glass fiber bundle includes preliminary dispersion of the glass fiber bundle and mixing with the impregnating agent to ensure the subsequent impregnation effect. The plurality of image information is 360° image information around the glass fiber bundle. The specific number is not limited, and the arrangement of the glass fiber bundle can be collected in all directions.

[0066] Specifically, the calculation process of the arrangement evaluation value includes:

[0067] After preprocessing the image information, the length and quantity of entanglement, crossing and agglomeration in the glass fiber bundle are determined based on an image recognition algorithm;

[0068] Substitute the length and amount into the following formula:

[0069] ,

[0070] Among them, P represents the arrangement evaluation value, α represents the weight coefficient of winding, and α is set to 0.3. i represents the length of the winding, i represents the number of winding positions, A 0 Indicates the minimum length allowed for winding, i 0 represents the minimum number of entanglements allowed, β represents the crossover weight coefficient, and β is set to 0.2. j represents the length of the crossover, j represents the number of crossover positions, B 0 Indicates the minimum length allowed for crossover, j 0 represents the minimum number of crossovers allowed, γ represents the weight coefficient of clustering, and γ=0.5 is set. k represents the length of the cluster, k represents the number of cluster positions, C 0 Indicates the minimum length of the cluster that can exist, k 0 Indicates the minimum number of clusters allowed to exist.

[0071] Specifically, the image preprocessing methods include, but are not limited to, denoising, graying, and contrast enhancement, which are not specifically limited and only need to meet the analysis requirements.

[0072] Specifically, the tensile test of long glass fiber reinforced materials is carried out according to standards, such as GB / T 1447-1983.

[0073] Specifically, the process of determining the wetting mode of the glass fiber bundle based on the arrangement evaluation value includes:

[0074] comparing the arrangement evaluation value with a preset arrangement evaluation value;

[0075] Based on the comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value, determining a first infiltration mode of starting the ultrasonic device for infiltration;

[0076] A second infiltration mode is determined in which the ultrasonic device is not turned on for infiltration based on a comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value.

[0077] Specifically, the ultrasonic device emits ultrasonic waves, which cover the wetting process of the glass fiber bundle and the plastic. The vibration caused by the ultrasonic waves drives the plastic to penetrate into the glass fiber bundle.

[0078] Specifically, ultrasonic vibration can promote the penetration and diffusion of the wetting agent, thereby improving the wetting effect of glass fiber and plastic.

[0079] Specifically, the process of determining the monitoring mode of the wetting effect of the glass fiber bundle based on the arrangement evaluation value includes:

[0080] comparing the arrangement evaluation value with a preset arrangement evaluation value;

[0081] Determining to perform monitoring in a first monitoring cycle based on a comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value;

[0082] Based on the comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value, it is determined to perform monitoring in the second monitoring cycle.

[0083] Specifically, a larger preset arrangement evaluation value indicates a worse arrangement orderliness of the glass fiber bundle. The value range of the preset arrangement evaluation value is set to [1, 3], and 2 is preferred in the embodiment of the present invention.

[0084] Specifically, the first monitoring period is 5 minutes, and the second monitoring period is 10 minutes.

[0085] Specifically, the process of establishing a mean value polyline based on the grayscale mean values ​​includes:

[0086] Determine the center point of the long glass fiber reinforced plastic section;

[0087] Divide the circle into several areas with the central point as the center and several preset distances as the radius;

[0088] Marking each of the regions in a direction extending from the edge of the cross-sectional image to the center of the circle as a first region, a second region, ..., an nth region;

[0089] Determine the grayscale average value corresponding to each of the regions, record the grayscale average value corresponding to the first region as a first average value, record the grayscale average value corresponding to the second region as a second average value, and record the grayscale average value corresponding to the nth region as an nth average value;

[0090] Each of the regions is a horizontal coordinate, and an average value polyline is established with each of the grayscale average values ​​as a vertical coordinate.

[0091] Specifically, the preset distance is determined according to the radius distance of the cross-section. For example, if the radius of the cross-section is 3 mm, the preset distance is 0.5 mm. The number of areas is 6. The 6th area is a circle with a radius of 0.5 mm and the 5th area is a circle with a radius of 1 mm and the center point as the center, which is the remaining ring excluding the circle in the 6th area, and so on.

[0092] Specifically, the grayscale average value of the corresponding area is determined according to an image recognition algorithm.

[0093] Specifically, the process of determining the degree of fit of the mean value polyline includes:

[0094] Determine a plurality of slope differences between corresponding positions of the mean value broken line and the standard broken line;

[0095] comparing the slope difference with a preset difference;

[0096] Determining that the slope of the average value polyline is qualified based on a comparison result that the slope difference is less than or equal to the preset difference;

[0097] The percentage of qualified slopes was counted and determined as the goodness of fit.

[0098] Specifically, an example is given for the corresponding position of the average value line and the standard line. For example, the line segment from the first area to the second area on the average value line corresponds to the line segment from the first area to the second area on the standard line. The slope difference can be obtained by comparing the slopes of the two line segments.

[0099] Specifically, the slope difference is the absolute value of the slope difference; the value range of the preset difference is set to [0.1 / mm, 0.5 / mm], and 0.2 / mm is preferred in the embodiment of the present invention.

[0100] Specifically, the standard broken line is the cross-sectional broken line of the long glass fiber reinforced plastic whose performance fully meets the requirements.

[0101] Specifically, the process of determining the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fit of the average value polyline includes:

[0102] comparing the fitness with a preset fitness;

[0103] Determining that the infiltration effect is unqualified based on the comparison result that the degree of fit is less than the preset degree of fit;

[0104] The infiltration effect is determined to be qualified based on the comparison result that the degree of fit is greater than or equal to the preset degree of fit.

[0105] Specifically, the preset fitness value range is set to [50%, 70%], and 60% is preferred in the embodiment of the present invention.

[0106] Specifically, the process of determining whether the coating property of a single glass fiber is qualified based on the interface spacing includes:

[0107] comparing the interface spacing with a preset spacing;

[0108] Determining that the coating property of the single glass fiber is unqualified based on the comparison result that the interface spacing is greater than the preset spacing;

[0109] Based on the comparison result that the interface spacing is less than or equal to the preset spacing, it is determined that the coating property of the single glass fiber is qualified.

[0110] Specifically, the value range of the preset spacing is set to [0.2nm, 0.5nm], and 0.3nm is preferred in the embodiment of the present invention.

[0111] Specifically, the process of determining the adjustment parameter based on the quantity ratio includes:

[0112] Comparing the quantity ratio with a preset ratio;

[0113] Determining to reduce the pulling speed of the glass fiber bundle based on a comparison result that the quantity ratio is greater than the preset ratio;

[0114] Based on the comparison result that the quantity proportion is less than or equal to the preset proportion, it is determined to increase the wetting temperature or the wetting pressure in the glass fiber reinforced plastic extrusion process.

[0115] Specifically, the smaller the pulling speed, the longer the impregnation time of the glass fiber and the better the impregnation effect.

[0116] Specifically, the value range of the preset proportion is set to [20%, 40%], and 30% is preferred in the embodiment of the present invention.

[0117] Specifically, under the condition of determining to reduce the traction speed, the quantity proportion is subtracted from the preset proportion to obtain a first proportion difference, and based on a comparison result that the first proportion difference is greater than a first preset proportion difference, it is determined to reduce the traction speed by a first speed adjustment coefficient;

[0118] Based on a comparison result that the first proportion difference is less than or equal to the first preset proportion difference, it is determined to reduce the traction speed by a second speed adjustment coefficient.

[0119] Specifically, the value range of the first preset proportion difference is set to [5%, 15%], and 10% is preferred in the embodiment of the present invention; the value range of the first speed adjustment coefficient is set to [0.82, 0.87], and 0.85 is preferred in the embodiment of the present invention; the value range of the second speed adjustment coefficient is set to [0.88, 0.96], and 0.93 is preferred in the embodiment of the present invention.

[0120] Specifically, under the condition of determining to adjust the extrusion process, the preset proportion is subtracted from the quantity proportion to obtain a second proportion difference, and based on a comparison result that the second proportion difference is greater than the second preset proportion difference, it is determined to increase the infiltration temperature by the temperature adjustment coefficient;

[0121] Based on the comparison result that the second proportion difference is less than or equal to the second preset proportion difference, it is determined to increase the infiltration pressure by the pressure adjustment coefficient.

[0122] Specifically, the value range of the second preset proportion difference is set to [2%, 5%), and 3% is preferred in the embodiment of the present invention; the value range of the temperature adjustment coefficient is set to [1.2, 1.3], and 1.25 is preferred in the embodiment of the present invention; the value range of the pressure adjustment coefficient is set to [1.1, 1.2], and 1.15 is preferred in the embodiment of the present invention.

[0123] Specifically, the method of using the adjustment coefficient to adjust the parameter is: the product of the original parameter and the adjustment coefficient is the adjusted parameter. For example, the process of using the pressure adjustment coefficient to adjust the infiltration pressure is: the infiltration pressure before adjustment × 1.15 = the infiltration pressure after adjustment.

[0124] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision, characterized in that: include: Acquire some image information of the pre-processed glass fiber bundle; Determining an arrangement evaluation value of the glass fiber filaments based on the image information, and determining a wetting mode of the glass fiber bundle and a monitoring frequency of the wetting effect based on the arrangement evaluation value; Under the determined infiltration mode and monitoring frequency, the long glass fiber reinforced plastic is subjected to a tensile test to obtain a cross-sectional image and the cross-sectional image is preprocessed, and a plurality of regions are divided with the center point of the cross section of the long glass fiber reinforced plastic as a reference point; Determine a plurality of grayscale average values ​​corresponding to each of the regions, establish an average value polyline based on each of the grayscale average values, and determine the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fit of the average value polyline; For unqualified wetting effects, the interface spacing between any glass fiber and the reinforced plastic is determined based on the cross-sectional image, whether the coating of a single glass fiber is qualified is determined based on the interface spacing, and the number ratio of glass fiber with unqualified coating is counted to determine the adjustment parameters based on the number ratio, wherein the adjustment parameters include the pulling speed of the glass fiber bundle, or adjusting the wetting temperature / wetting pressure of the glass fiber reinforced plastic extrusion process; The process of determining the wetting mode of the glass fiber bundle based on the arrangement evaluation value includes: comparing the arrangement evaluation value with a preset arrangement evaluation value; Based on the comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value, determining that the infiltration mode is a first infiltration mode in which the ultrasonic device is turned on for infiltration; Determining the infiltration mode as a second infiltration mode in which the ultrasonic device is not turned on for infiltration based on a comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value; The process of determining the monitoring mode of the wetting effect of the glass fiber bundle based on the arrangement evaluation value includes: comparing the arrangement evaluation value with a preset arrangement evaluation value; Determining to perform monitoring in a first monitoring cycle based on a comparison result that the arrangement evaluation value is greater than the preset arrangement evaluation value; Determining to perform monitoring in a second monitoring cycle based on a comparison result that the arrangement evaluation value is less than or equal to the preset arrangement evaluation value; The process of establishing a mean value polyline based on each of the grayscale mean values ​​comprises: Determine the center point of the long glass fiber reinforced plastic section; Divide the circle into several areas with the central point as the center and several preset distances as the radius; Marking each of the regions in a direction extending from the edge of the cross-sectional image to the center of the circle; Establishing an average value polyline with each of the regions as the abscissa and each of the grayscale average values ​​as the ordinate; The process of determining the goodness of fit of the mean polyline includes: Determine a plurality of slope differences between corresponding positions of the mean value broken line and the standard broken line; comparing the slope difference with a preset difference; Determining that the slope of the average value polyline is qualified based on a comparison result that the slope difference is less than or equal to the preset difference; The percentage of qualified slopes is calculated and the percentage is determined as the goodness of fit; The calculation process of the arrangement evaluation value includes: After preprocessing the image information, the length and quantity of entanglement, crossing and agglomeration in the glass fiber bundle are determined based on an image recognition algorithm; Substitute the length and amount into the following formula: Among them, P represents the arrangement evaluation value, α represents the winding weight coefficient, and a i represents the length of the winding, i represents the number of winding positions, A0 represents the minimum length of the winding, i0 represents the minimum number of windings allowed, β represents the crossover weight coefficient, b j represents the length of the crossover, j represents the number of crossover positions, B0 represents the minimum length of the crossover allowed, j0 represents the minimum number of crossovers allowed, γ represents the weight coefficient of the clustering, c k represents the length of the cluster, k represents the number of cluster positions, C0 represents the minimum length of the cluster, and k0 represents the minimum number of clusters.

2. The method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to claim 1, characterized in that: The process of determining the eligibility of the wetting effect of the long glass fiber reinforced plastic based on the fit of the mean value polyline includes: comparing the fitness with a preset fitness; Based on the comparison result that the degree of fit is less than the preset degree of fit, it is determined that the infiltration effect is unqualified.

3. The method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to claim 2, characterized in that: The process of determining whether the coating property of a single glass fiber is qualified based on the interface spacing includes: comparing the interface spacing with a preset spacing; Based on the comparison result that the interface spacing is greater than the preset spacing, it is determined that the coating property of the single glass fiber is unqualified.

4. The method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to claim 3, characterized in that: The process of determining the adjustment parameter based on the quantity ratio includes: Comparing the quantity ratio with a preset ratio; Determining to reduce the pulling speed of the glass fiber bundle based on the comparison result that the quantity ratio is greater than the preset ratio; Based on the comparison result that the quantity proportion is less than or equal to the preset proportion, it is determined to increase the wetting temperature or the wetting pressure in the glass fiber reinforced plastic extrusion process.

5. The method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to claim 4, characterized in that: Under the condition of determining to reduce the traction speed, subtract the quantity proportion from the preset proportion to obtain a first proportion difference, and determine to reduce the traction speed by a first speed adjustment coefficient based on a comparison result that the first proportion difference is greater than a first preset proportion difference; Based on a comparison result that the first proportion difference is less than or equal to the first preset proportion difference, it is determined to reduce the traction speed by a second speed adjustment coefficient.

6. The method for monitoring the wetting effect of long glass fiber reinforced plastics based on machine vision according to claim 4, characterized in that: Under the condition of determining to adjust the extrusion process, subtract the preset proportion from the quantity proportion to obtain a second proportion difference, and determine to increase the infiltration temperature by the temperature adjustment coefficient based on a comparison result that the second proportion difference is greater than the second preset proportion difference; Based on the comparison result that the second proportion difference is less than or equal to the second preset proportion difference, it is determined to increase the infiltration pressure by the pressure adjustment coefficient.

Images