Glass fiber direct yarn detection system based on mirror reflection and detection method thereof

Abstract

The invention discloses a glass fiber direct yarn detection system based on mirror reflection and a detection method thereof, whether a bushing yarn outlet hole is blocked or not is detected in a mirror reflection mode, a special waste yarn cleaning mechanism is designed, when it is detected that the bushing yarn outlet hole is blocked, glass fiber direct yarn production equipment is switched to enter a waste yarn treatment process, and the detection efficiency is improved. And the waste yarn cleaning mechanism is used for collecting the glass fiber direct yarns below the bushing and guiding the glass fiber direct yarns to a waste yarn storage area. According to the application, the leakage plate blockage can be automatically detected, and after the leakage plate blockage is detected, the glass fiber direct yarn which does not meet the quality requirement is subjected to automatic intervention treatment.

Description

Technical Field

[0001] The present application relates to the technical field of glass fiber direct yarn detection, and in particular to a glass fiber direct yarn detection system and a detection method thereof based on mirror reflection. Background Art

[0002] Glass fiber direct yarn is directly drawn from a leak plate. However, during the production process, the yarn outlet hole of the leak plate is often blocked, causing production failures of glass fiber direct yarn, affecting the product quality of glass fiber direct yarn. Therefore, when the yarn outlet hole of the leak plate is blocked, intervention is required. However, due to the high temperature of the leak plate, the hole diameter of the yarn outlet hole of the leak plate is 0.1mm-0.5mm, or even smaller, and there are cooling water devices and other mechanisms at the outlet of the leak plate, the space is small, and the water mist is large under the influence of the high temperature of the leak plate, making it difficult for industrial cameras to directly image, difficult to detect using automated detection methods, and difficult to achieve automated production.

[0003] At present, manual intervention is mostly used. During the production process, the yarn outlet hole of the leaking plate is manually observed to see if it is blocked. When blockage is observed, manual intervention is performed (i.e., the glass fiber direct yarn produced during the period when the yarn outlet hole is blocked is manually gathered and guided to the waste yarn area). When the glass fiber at the blocked yarn outlet hole becomes unobstructed again under the driving force of tension, the manual intervention process is exited. This manual intervention method has low work efficiency and high production cost throughout the process, and consumes a lot of manpower and material resources. In addition, the blockage of the yarn outlet hole of the leaking plate is often not discovered in time, resulting in a large waste of production materials and affecting product quality.

[0004] Therefore, how to realize automatic detection of leak plate blockage and automatically intervene in the glass fiber direct yarn that does not meet the quality requirements after the leak plate blockage is detected is a problem that needs to be solved urgently in the current field. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a glass fiber direct yarn detection system and a detection method based on mirror reflection, which can realize automatic detection of leak plate blockage and automatically intervene in the glass fiber direct yarn that does not meet the quality requirements after detecting the leak plate blockage.

[0006] The first object of the present application is to provide a glass fiber direct yarn detection system based on specular reflection.

[0007] The above-mentioned application objective 1 of the present application is achieved through the following technical solutions:

[0008] A glass fiber direct yarn detection system based on specular reflection, comprising:

[0009] An image acquisition module is arranged on one side of the leak plate of the glass fiber direct yarn to be detected and is located below the leak plate, and is used to collect a surface image of the yarn outlet side of the leak plate in a working state in real time based on a mirror reflection method to obtain a leak plate detection image;

[0010] An image processing module, which is used to perform yarn outlet hole detection processing on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to characterize whether the yarn outlet hole of the leak plate is blocked;

[0011] A process switching module, which is used to switch the glass fiber direct yarn production equipment into a corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process, and when the visual inspection result data indicates that the yarn outlet hole of the leak plate has a clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the waste yarn processing process, and when the visual inspection result data indicates that the yarn outlet hole of the leak plate has no clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the normal process; and

[0012] The waste yarn cleaning module includes a waste yarn collecting mechanism and a waste yarn guiding mechanism, wherein:

[0013] The waste yarn bundling mechanism is arranged on one side of the leaking plate and is located below the leaking plate. The waste yarn bundling mechanism is used to bundle the glass fiber direct yarn below the leaking plate into a bundle when the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process;

[0014] The waste yarn guiding mechanism is arranged below the leaking plate, and is used to guide the bundled glass fiber direct yarn to a preset waste yarn storage area.

[0015] Preferably, the image acquisition module comprises:

[0016] A closed shell, wherein the closed shell is provided with a detection port facing the leak plate, and a high-temperature resistant and highly transparent tempered glass is sealed and installed at the detection port; and

[0017] A mirror imaging system comprises an industrial camera and a plane reflector, wherein the industrial camera and the plane reflector are arranged in the closed shell, the reflective surface of the plane reflector faces the detection port, the plane reflector is used to reflect the surface image of the yarn outlet side of the leak plate to the industrial camera, and the industrial camera is used to collect the surface image of the yarn outlet side of the leak plate reflected by the plane reflector to obtain the leak plate detection image.

[0018] Preferably, the image acquisition module further includes:

[0019] The water mist self-cleaning system comprises a high-pressure air pipe and a high-pressure nozzle, wherein the high-pressure air pipe and the high-pressure nozzle are arranged outside the closed shell, the high-pressure nozzle is connected to the air outlet of the high-pressure air pipe, and the high-pressure nozzle is used to output a high-pressure airflow to sweep the outer surface of the high-transparency tempered glass, so as to blow away the dust and water mist that will fall on the outer surface of the high-transparency tempered glass.

[0020] Preferably, the image acquisition module further includes:

[0021] A positive pressure cooling system includes an air inlet nozzle arranged on a side panel on one side of the closed shell and an exhaust fan arranged on a side panel on the other side of the closed shell opposite to the side panel on the side where the air inlet nozzle is located. The positive pressure cooling system is used to cool the industrial camera.

[0022] Preferably, the waste yarn collecting mechanism comprises:

[0023] A converging gripper, comprising two clamping jaws arranged opposite to each other;

[0024] A first driving assembly is connected to the two clamping jaws of the converging gripper, and the first driving assembly is used to drive the two clamping jaws of the converging gripper to move closer to or away from each other, so as to close or open the converging gripper;

[0025] The second driving assembly is drivingly connected to the first driving assembly, and the second driving assembly is used to drive the gathering gripper on the first driving assembly to approach or move away from the glass fiber direct yarn under the leaking plate.

[0026] Preferably, the yarn outlet hole detection processing is performed on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data including:

[0027] The position of the leaking board in the leaking board detection image is identified and located by a template matching algorithm, and the image area corresponding to the leaking board in the leaking board detection image is extracted to obtain a leaking board image;

[0028] In combination with the template size, adaptively scaling the leak plate image to make it consistent with the template size;

[0029] Segmenting the leak plate image into multiple regions to obtain multiple leak plate region images;

[0030] Perform threshold segmentation on each of the leak plate area images to obtain a hole area image and a non-hole area image corresponding to each of the leak plate area images;

[0031] Using an edge detection algorithm to extract edge contour information of holes in the hole area images corresponding to each of the leak plate area images;

[0032] According to the extracted edge contour information, a circular hole fitting algorithm is used to perform circular hole fitting on the edge contour of the hole, and a hole area image after circular hole fitting is obtained;

[0033] Calculate the number and diameter of circular holes in the corresponding leak plate region image based on the hole region image after circular hole fitting;

[0034] According to the number and diameter of the circular holes in the leak plate area image, it is judged whether there is hole blockage in the leak plate area corresponding to the leak plate area image, and the visual detection result data is obtained.

[0035] Preferably, the glass fiber direct yarn detection system based on specular reflection further comprises:

[0036] A database, used to store the visual inspection result data; and

[0037] A data analysis module is used to analyze the visual inspection result data within a preset time period, calculate the CPK index of the glass fiber direct yarn production equipment and monitor the production quality of the glass fiber direct yarn.

[0038] Preferably, the performing of data analysis on the visual inspection result data within a preset period of time to calculate the CPK index of the glass fiber direct yarn production equipment comprises:

[0039] Through the time series analysis method, the average value and standard deviation of the number of circular holes in each leak plate area image in the visual inspection result data within a preset time period are analyzed, and the CPK index of the glass fiber direct yarn production equipment is calculated based on the preset CPK calculation formula.

[0040] Preferably, the step of analyzing the visual inspection result data within a preset period of time to monitor the production quality of the glass fiber direct yarn includes:

[0041] Compare and judge the circular hole quantity detection value and circular hole diameter detection value of each leak plate area image in the visual inspection result data within a preset time period with the corresponding standard value, analyze the current production status of the glass fiber direct yarn, and obtain the production status analysis result of each leak plate area;

[0042] The relationship model between the round hole number detection value, the round hole diameter detection value and the quality of the glass fiber direct yarn product is determined by time series analysis method based on the round hole number detection value, the round hole diameter detection value and the production status analysis results of each leak plate area;

[0043] The relationship model is trained using a grey wolf optimization algorithm to obtain a production quality monitoring model;

[0044] The quality of glass fiber direct yarn products is monitored based on the production quality monitoring model.

[0045] The second object of the present application is to provide a detection method for a glass fiber direct yarn detection system based on mirror reflection as described in any one of the above-mentioned application objects.

[0046] The second application objective of the present application is achieved through the following technical solutions:

[0047] A method for detecting direct glass fiber yarn based on specular reflection, characterized in that it comprises the following steps:

[0048] S1, the image acquisition module collects the surface image of the yarn outlet side of the leak plate in the working state in real time to obtain the leak plate detection image;

[0049] S2, the image processing module performs yarn outlet hole detection processing on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to characterize whether the yarn outlet hole of the leak plate is blocked;

[0050] S3, the process switching module switches the glass fiber direct yarn production equipment into the corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate has a clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the waste yarn processing process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate has no clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the normal process; wherein,

[0051] When the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process, the waste yarn gathering mechanism gathers the glass fiber direct yarn under the leak plate into a bundle, and the waste yarn guiding mechanism guides the gathered glass fiber direct yarn to the preset waste yarn storage area.

[0052] The above technical solution of the present application has the following advantages compared with the prior art:

[0053] The present application detects whether the yarn outlet hole of the leak plate is blocked by means of mirror reflection, and designs a special waste yarn cleaning mechanism. When it is detected that the yarn outlet hole of the leak plate is blocked, the glass fiber direct yarn production equipment is switched to enter the waste yarn processing flow, and the waste yarn cleaning mechanism is used to gather the glass fiber direct yarn under the leak plate and guide it to the waste yarn storage area. The automatic detection of leak plate blockage can be realized, and the glass fiber direct yarn that does not meet the quality requirements can be automatically intervened after the leak plate blockage is detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 It is a schematic diagram of the three-dimensional structure of a glass fiber direct yarn detection system based on mirror reflection in an embodiment of the present application;

[0056] Figure 2 Schematic diagram of the three-dimensional structure of the image acquisition module in the embodiment of the present application;

[0057] Figure 3 for Figure 2 The main view of the image acquisition module shown is right;

[0058] Figure 4 for Figure 2 A schematic diagram of a partial three-dimensional structure of an image acquisition module shown;

[0059] Figure 5 This is a schematic diagram of the three-dimensional structure of the waste yarn bundling mechanism in the embodiment of the present application;

[0060] Figure 6 This is a schematic diagram of the three-dimensional structure of the waste yarn guiding mechanism in the embodiment of the present application;

[0061] Figure 7 This is a principle block diagram of a glass fiber direct yarn detection system based on mirror reflection in an embodiment of the present application;

[0062] Figure 8 It is a partial schematic diagram of a leak plate detection image when the yarn outlet hole of the leak plate is not blocked in the embodiment of the present application;

[0063] Fig. 9 It is a partial schematic diagram of a leak plate detection image when the yarn outlet hole of the leak plate is blocked in the embodiment of the present application;

[0064] Fig.10A schematic diagram of a process for analyzing visual inspection result data within a preset time period and monitoring the production quality of glass fiber direct yarn in an embodiment of the present application;

[0065] Fig.11 This is a flow chart of a detection method of a glass fiber direct yarn detection system based on mirror reflection in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0067] In the embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely schematic. For example, the division of units and modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or modules can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0068] In addition, all functional units in the embodiments of the present application may be integrated into one processor, or each unit may be a separate device, or two or more units may be integrated into one device; each functional unit in the embodiments of the present application may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0069] A person skilled in the art can understand that all or part of the steps of the following method embodiments can be completed by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, the steps of the following method embodiments are executed; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and other media that can store program codes.

[0070] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "multiple" and "several" mean two or more, unless otherwise clearly and specifically defined.

[0071] like Figure 1-7 As shown, an embodiment of the present application provides a glass fiber direct yarn detection system based on mirror reflection, which may include:

[0072] An image acquisition module 1 is arranged on one side of the leak plate 100 of the glass fiber direct yarn 200 to be detected and is located below the leak plate 100. The image acquisition module 1 is used to collect the surface image of the yarn outlet side of the leak plate 100 in the working state in real time based on the mirror reflection method to obtain the detection image of the leak plate 100;

[0073] An image processing module 2 is used to perform yarn outlet hole 101 detection processing on the detection image of the leak plate 100 according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to characterize whether the yarn outlet hole 101 of the leak plate 100 is blocked;

[0074] A process switching module 3 is used to switch the glass fiber direct yarn production equipment into a corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process. When the visual inspection result data indicates that the yarn outlet hole 101 of the leak plate 100 is clogged, the process switching module 3 switches the glass fiber direct yarn production equipment into the waste yarn processing process. When the visual inspection result data indicates that the yarn outlet hole 101 of the leak plate 100 is not clogged, the process switching module 3 switches the glass fiber direct yarn production equipment into the normal process; and

[0075] The waste yarn cleaning module 4 comprises a waste yarn collecting mechanism 41 and a waste yarn guiding mechanism 42, wherein:

[0076] The waste yarn collecting mechanism 41 is arranged on one side of the leaking plate 100 and is located below the leaking plate 100. The waste yarn collecting mechanism 41 is used to collect the glass fiber direct yarn 200 below the leaking plate 100 into a bundle when the process switching module 3 switches the glass fiber direct yarn production equipment to enter the waste yarn processing process;

[0077] The waste yarn guiding mechanism 42 is disposed below the leaking plate 100 and is used to guide the bundled glass fiber direct yarn 200 to a preset waste yarn storage area.

[0078] The glass fiber direct yarn 200 detection system based on mirror reflection in the embodiment of the present application detects whether the yarn outlet hole 101 of the leak plate 100 is blocked by mirror reflection, and is designed with a special waste yarn cleaning mechanism. When it is detected that the yarn outlet hole 101 of the leak plate 100 is blocked, the glass fiber direct yarn production equipment is switched to enter the waste yarn processing flow, and the waste yarn cleaning mechanism is used to gather the glass fiber direct yarn 200 under the leak plate 100 and guide it to the waste yarn storage area. It can realize automatic detection of blockage of the leak plate 100, and automatically intervene in the glass fiber direct yarn 200 that does not meet the quality requirements after detecting that the leak plate 100 is blocked.

[0079] In one embodiment, the image acquisition module 1 includes:

[0080] A closed housing 11 is provided with a detection port facing the leak plate 100, and a high-temperature resistant and highly transparent tempered glass 12 is sealed and installed at the detection port; and

[0081] The mirror imaging system 13 includes an industrial camera 131 and a plane reflector 132. The industrial camera 131 and the plane reflector 132 are arranged in a closed shell 11. The reflective surface of the plane reflector 132 faces the detection port. The plane reflector 132 is used to reflect the surface image of the yarn outlet side of the leak plate 100 to the industrial camera 131. The industrial camera 131 is used to collect the surface image of the yarn outlet side of the leak plate 100 reflected by the plane reflector 132 to obtain a detection image of the leak plate 100.

[0082] Since the temperature of the leak plate 100 is relatively high, the aperture of the yarn outlet hole 101 of the leak plate 100 is small, and there is a cooling water device and other mechanisms at the outlet of the leak plate 100, the space is small, and the water mist is large under the influence of the high temperature of the leak plate 100, which makes it difficult for the industrial camera 131 to directly image. In this embodiment, by arranging the industrial camera 131 and the plane reflector 132 of the mirror imaging system 13 in a sealed closed shell 11, the interference of the external high temperature environment is effectively avoided, and the problem that the industrial camera 131 cannot be used directly to collect images due to the small space is effectively solved through the mirror radiation method. When in use, the plane reflector 132 reflects the surface image of the yarn outlet side of the leak plate 100 to the industrial camera 131 based on the principle of mirror reflection, and the industrial camera 131 collects the surface image to obtain the detection image of the leak plate 100.

[0083] In this embodiment, in order to solve the problem that the industrial camera 131 is affected by temperature and has difficulty in high-definition imaging, mirror reflection is used to achieve high-definition imaging, thereby achieving high-quality imaging of the yarn outlet hole 101 of the leak plate 100.

[0084] In one embodiment, the image acquisition module 1 also includes a water mist self-cleaning system 14, which includes a high-pressure air pipe 141 and a high-pressure nozzle 142. The high-pressure air pipe 141 and the high-pressure nozzle 142 are arranged outside the closed shell 11, and the high-pressure nozzle 142 is connected to the air outlet of the high-pressure air pipe 141. The high-pressure nozzle 142 is used to output a high-pressure airflow to sweep the outer surface of the high-transparency tempered glass 12 to blow away the dust and water mist that will fall on the outer surface of the high-transparency tempered glass 12.

[0085] During the process of image acquisition by the mirror imaging system 13, high-pressure air is introduced into the high-pressure air pipeline and sprayed out through the high-pressure nozzle 142 to sweep the outer surface of the high-transparency tempered glass 12, thereby blowing away dust and water mist that will fall on the outer surface of the high-transparency tempered glass 12, effectively avoiding the influence of large water mist on image acquisition under the influence of high temperature of the leak plate 100.

[0086] In this embodiment, since the imaging system is easily affected by water mist, the mirror imaging system 13 is installed in a closed space, a glass window made of high-temperature resistant high-transparency tempered glass 12 is used, and a water mist self-cleaning system 14 is combined to achieve the stability of high-definition imaging.

[0087] In one embodiment, the image acquisition module 1 further includes:

[0088] The positive pressure cooling system 15 includes an air inlet nozzle 151 arranged on a side panel on one side of the closed shell 11 and an exhaust fan 152 arranged on a side panel on the other side of the closed shell 11 opposite to the side panel on the side where the air inlet nozzle 151 is located. The positive pressure cooling system 15 is used to cool the industrial camera 131.

[0089] When in use, positive-pressure cooling air is blown into the closed shell 11 from the air inlet nozzle 151 to cool the industrial camera 131 in the closed shell 11. The positive-pressure cooling air after heat exchange automatically flows out of the closed shell 11 due to the pressure difference between it and the outside world. In order to improve the cooling effect, an exhaust fan 152 can be used to suck the air after heat exchange in the closed shell 11 to accelerate the circulation of the positive-pressure cooling air and achieve rapid cooling of the industrial camera 131.

[0090] In this embodiment, in a closed space, positive pressure air and an exhaust fan 152 are used to cool the system to prevent the industrial camera 131 from being damaged by a high temperature environment.

[0091] In one embodiment, the waste yarn collecting mechanism 41 comprises:

[0092] A converging gripper 411, which includes two clamping jaws arranged opposite to each other;

[0093] A first driving assembly 412, which is drivingly connected to the two clamping jaws of the converging gripper 411, and the first driving assembly 412 is used to drive the two clamping jaws of the converging gripper 411 to move closer to or away from each other, so as to close or open the converging gripper 411;

[0094] The second driving assembly 413 is drivingly connected to the first driving assembly 412 , and is used to drive the gathering gripper 411 on the first driving assembly 412 to move closer to or away from the glass fiber direct yarn 200 below the leaking plate 100 .

[0095] When the process switching module 3 switches the glass fiber direct yarn production equipment to enter the waste yarn processing process, the second driving component 413 of the waste yarn bundling mechanism 41 drives the bundling gripper 411 on the first driving component 412 to approach the glass fiber direct yarn 200 under the leak plate 100. When the bundling gripper 411 moves into place, the first driving component 412 drives the two jaws of the bundling gripper 411 to approach each other to close the bundling gripper 411, and the glass fiber direct yarn 200 with quality problems currently under the leak plate 100 is gathered into a bundle. The second driving component 413 then drives the bundling gripper 411 on the first driving component 412 to be pulled to the waste yarn guiding mechanism 42 and handed over to the waste yarn guiding mechanism 42 for processing. Then the first driving component 412 drives the two jaws of the bundling gripper 411 to move away from each other to open the bundling gripper 411 to release the bundled glass fiber direct yarn 200. The second driving component 413 then drives the bundling gripper 411 on the first driving component 412 to move to the initial position and wait for the next work instruction.

[0096] In this embodiment, the waste yarn bundling mechanism 41 formed by the bundling gripper 411, the first driving assembly 412 and the second driving assembly 413 is used to bundle the waste yarn and pull it to the waste yarn guiding mechanism 42, thereby realizing the automated processing of the waste yarn bundling.

[0097] Specifically, in one embodiment, the waste yarn guiding mechanism 42 includes two friction wheels 422 installed in parallel on a mounting frame 421, and a gap is provided between the two friction wheels 422 for the waste yarn to enter and guide the waste yarn. When in use, the two friction wheels 422 rotate toward each other, and under the friction traction of the two friction wheels 422, the waste yarn bundle pulled by the waste yarn collecting mechanism 41 is guided to a preset waste yarn storage area.

[0098] As the waste yarn guide mechanism 42 pulls, the raw material of the glass fiber direct yarn 200 in a molten state above the leak plate 100 keeps flowing, so that the blocked leaking yarn hole becomes unobstructed again. At this time, the visual inspection result data obtained after the detection image of the leak plate 100 acquired by the image acquisition module 1 and processed by the image processing module 2 indicates that there is no hole blockage in the yarn outlet hole 101 of the leak plate 100, and the process switching module 3 switches the glass fiber direct yarn production equipment to enter the normal process according to the visual inspection result data that there is no hole blockage at present, and the glass fiber direct yarn 200 that meets the quality requirements leaking from the yarn outlet hole 101 of the leak plate 100 is wound into a roll by the yarn winding structure in the glass fiber direct yarn production equipment to form a normal product.

[0099] Specifically, in this embodiment, the first driving component 412 adopts a forward and reverse bidirectional linear module driven by a double-headed cylinder (or a forward and reverse ball screw), and the two jaws of the converging gripper 411 are relatively installed and fixed on the two sliders of the forward and reverse bidirectional linear module; the second driving component 413 adopts a linear module driven by a telescopic cylinder (or a ball screw), and the forward and reverse bidirectional linear module is installed and fixed on the slider of the linear module.

[0100] In one embodiment, the yarn outlet hole 101 detection processing is performed on the detection image of the leak plate 100 according to a preset image processing algorithm, and the visual detection result data obtained includes:

[0101] The position of the leak plate 100 in the leak plate 100 detection image is identified and located by a template matching algorithm, and the image area corresponding to the leak plate 100 in the leak plate 100 detection image is extracted to obtain the leak plate 100 image;

[0102] Combined with the template size, the image of the leak plate 100 is adaptively scaled to make it consistent with the template size, so as to facilitate subsequent hole blockage identification;

[0103] The image of the leak plate 100 is segmented into multiple regions to obtain multiple images of the leak plate 100 regions. Since the leak plate 100 has many holes (generally 2000 or 4000 holes), in this embodiment, the image of the leak plate 100 is segmented into multiple regions to form multiple images of the leak plate 100 regions, which is convenient for subsequent partition processing during hole blockage detection and improves the detection speed.

[0104] Perform threshold segmentation on each leak plate 100 area image to obtain a hole area image and a non-hole area image corresponding to each leak plate 100 area image; that is, by performing threshold segmentation on each leak plate 100 area image, holes and other objects are distinguished;

[0105] An edge detection algorithm is used to extract edge contour information of holes in the hole area image corresponding to each leak plate 100 area image; when detecting each leak plate 100 area image, it can be performed sequentially or simultaneously in parallel;

[0106] According to the extracted edge contour information, a circular hole fitting algorithm is used to perform circular hole fitting on the edge contour of the hole, and a hole area image after circular hole fitting is obtained;

[0107] Based on the hole area image after the circular hole fitting, the number and diameter of the circular holes in the corresponding area image of the leak plate 100 are calculated;

[0108] According to the number and diameter of the circular holes in the entire leak plate 100 area image corresponding to the leak plate 100, it is determined whether there is hole blockage in the leak plate 100 area corresponding to the leak plate 100 area image, and visual detection result data is obtained.

[0109] In this embodiment, the above-mentioned image processing algorithm is used to perform yarn outlet hole 101 detection processing on the detection image of the leak plate 100, so as to quickly and accurately obtain visual detection result data that can characterize whether there is a hole blockage in the leak plate 100.

[0110] Specifically, Figure 8 , Fig. 9 As shown, Figure 8 1 is a partial schematic diagram of a detection image of the leak plate 100 when the yarn outlet hole 101 of the leak plate 100 is not blocked in the embodiment of the present application. Fig. 9 This is a partial schematic diagram of the detection image of the leak plate 100 when the yarn outlet hole 101 of the leak plate 100 in the embodiment of the present application is blocked (the black dot in the yellow box is the blocked yarn outlet hole 101). By comparison, it can be found that when the yarn outlet hole 101 is blocked, the glass fiber direct yarn 200 raw material in a molten state accumulates around the yarn outlet hole 101, so that the diameter of the yarn outlet hole 101 will increase. Therefore, according to the number of circular holes and the diameter of the circular holes in the entire leak plate 100 area image corresponding to the leak plate 100, it is judged whether there is hole blockage in the leak plate 100 area corresponding to the leak plate 100 area image, and the hole blockage condition of the yarn outlet hole 101 can be accurately judged.

[0111] In one embodiment, the glass fiber direct yarn 200 detection system based on specular reflection further includes:

[0112] A database for storing visual inspection result data; and

[0113] The data analysis module is used to analyze the visual inspection result data within a preset time period, calculate the CPK index of the glass fiber direct yarn production equipment and monitor the production quality of the glass fiber direct yarn 200.

[0114] In this embodiment, the data analysis module is used to perform data analysis on the visual inspection result data within a preset time period to calculate the CPK (Complex Process Capability index) index of the glass fiber direct yarn production equipment and monitor the production quality of the glass fiber direct yarn 200, so that the relevant process parameters of the glass fiber direct yarn production equipment can be adjusted according to the calculated CPK index and the monitored production quality of the glass fiber direct yarn 200.

[0115] In one embodiment, data analysis is performed on the visual inspection result data within a preset period of time to calculate the CPK index of the glass fiber direct yarn production equipment, including:

[0116] Through the time series analysis method, the average value and standard deviation of the number of circular holes in each leak plate 100 area image in the visual inspection result data within the preset time period are analyzed, and the CPK index of the glass fiber direct yarn production equipment is calculated based on the preset CPK calculation formula.

[0117] The specific analysis process is as follows:

[0118] 1. Determine the upper and lower limits of the standard value of the number of round holes;

[0119] 2. Store the number of round holes (1min / group);

[0120] 3. Calculation of the average and standard deviation of N-day data;

[0121] 4. Calculate the CPK index of the glass fiber direct yarn production equipment during N days of production according to the CPK calculation formula.

[0122] The specific calculation formula of CPK index is:

[0123] CPK = Min [(upper limit of the number of round holes - average value of N-day data) / (3*N-day data standard deviation), (average value of N-day data - lower limit of the number of round holes) / (3*N-day data standard deviation)]

[0124] Among them, N days can be selected according to production needs, the upper limit of the number of round holes is the total number of yarn outlet holes 101 of the leak plate 100, and the lower limit of the number of round holes is a parameter set according to the actual requirements of product quality.

[0125] In one embodiment, analyzing the visual inspection result data within a preset period of time to monitor the production quality of the glass fiber direct yarn 200 includes:

[0126] Compare and judge the circular hole quantity detection value and circular hole diameter detection value of each leak plate 100 area image in the visual inspection result data within the preset time period with the corresponding standard value, analyze the current production status of the glass fiber direct yarn 200, and obtain the production status analysis result of each leak plate 100 area;

[0127] The relationship model between the circular hole number detection value, the circular hole diameter detection value and the product quality of the glass fiber direct yarn 200 is determined based on the circular hole number detection value, the circular hole diameter detection value and the production status analysis results of each leak plate 100 area through the time series analysis method; specifically, the circular hole number detection value and the circular hole diameter detection value are used as the input of the data set, and the production status analysis results of the glass fiber direct yarn 200 (i.e., the product quality of the glass fiber direct yarn 200) are used as the data set output value to form a data set, and the data set is divided into 90% of the data as a training data set and the remaining 10% of the data as a test data set, and a long short-term memory neural network (LSTM) is used to build a relationship model between the detection parameters (circular hole number detection value and circular hole diameter detection value) and the quality of the glass fiber direct yarn 200;

[0128] The Gray Wolf Optimization Algorithm is used to train the relational model to obtain a production quality monitoring model; that is, the Gray Wolf Optimization Algorithm is used to obtain the optimal network hyperparameter value of LSTM to obtain a highly accurate production quality monitoring model, namely, the GWO-LSTM relational model;

[0129] The product quality of glass fiber direct yarn 200 is monitored based on the production quality monitoring model. Finally, the production quality of glass fiber direct yarn 200 is monitored according to the built GWO-LSTM relationship model through the detection data, and the process parameters of the production process of glass fiber direct yarn 200 such as temperature, humidity, input material amount, etc. are analyzed through the production quality of glass fiber direct yarn 200, providing technical support for the optimization of the process parameters of the production process of glass fiber direct yarn 200.

[0130] Specifically, in this embodiment, the visual inspection result data within a preset period is analyzed to monitor the production quality of the glass fiber direct yarn. Fig.10 shown.

[0131] The image processing module 2 and the process switching module 3 in this embodiment can adopt computer equipment installed with corresponding image processing software and control programs, such as industrial computers, PCs, PLC controllers, MCU controllers, etc.

[0132] like Fig.11 As shown, an embodiment of the present application provides a glass fiber direct yarn detection method based on mirror reflection, which is implemented based on the glass fiber direct yarn detection system based on mirror reflection in any of the above embodiments, and the method may include the following steps:

[0133] S1, the image acquisition module collects the surface image of the yarn outlet side of the leak plate in the working state in real time to obtain the leak plate detection image;

[0134] S2, the image processing module performs yarn outlet hole detection processing on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to characterize whether the yarn outlet hole of the leak plate is blocked;

[0135] S3, the process switching module switches the glass fiber direct yarn production equipment to enter the corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate is clogged, the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate is not clogged, the process switching module switches the glass fiber direct yarn production equipment to enter the normal process; wherein,

[0136] When the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process, the waste yarn gathering mechanism gathers the glass fiber direct yarn under the leak plate into a bundle, and the waste yarn guiding mechanism guides the gathered glass fiber direct yarn to the preset waste yarn storage area.

[0137] It should be noted that the working principle of the glass fiber direct yarn detection method based on mirror reflection in this embodiment is the same as the working principle of the glass fiber direct yarn detection system based on mirror reflection in the above embodiment, which will not be repeated here.

[0138] Since the glass fiber direct yarn detection method based on mirror reflection in the present embodiment is implemented by using the glass fiber direct yarn detection system based on mirror reflection in the above-mentioned embodiment, the beneficial effects of the glass fiber direct yarn detection method based on mirror reflection in the present embodiment are the same as the beneficial effects of the glass fiber direct yarn detection system based on mirror reflection in the above-mentioned embodiment.

[0139] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0140] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this embodiment can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] The steps of the method or algorithm described in the embodiments disclosed in this embodiment can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0142] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined in the present embodiment may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown in the present embodiment, but will conform to the widest scope consistent with the principles and novel features disclosed in the present embodiment.

Claims

1. A glass fiber direct yarn detection system based on specular reflection, characterized in that: include: An image acquisition module is arranged on one side of the leak plate of the glass fiber direct yarn to be detected and is located below the leak plate, and is used to collect a surface image of the yarn outlet side of the leak plate in a working state in real time based on a mirror reflection method to obtain a leak plate detection image; An image processing module, which is used to perform yarn outlet hole detection processing on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to characterize whether the yarn outlet hole of the leak plate is blocked; A process switching module, which is used to switch the glass fiber direct yarn production equipment into a corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process, and when the visual inspection result data indicates that the yarn outlet hole of the leak plate has a clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the waste yarn processing process, and when the visual inspection result data indicates that the yarn outlet hole of the leak plate has no clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the normal process; and The waste yarn cleaning module includes a waste yarn collecting mechanism and a waste yarn guiding mechanism, wherein: The waste yarn bundling mechanism is arranged on one side of the leaking plate and is located below the leaking plate. The waste yarn bundling mechanism is used to bundle the glass fiber direct yarn below the leaking plate into a bundle when the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process; The waste yarn guiding mechanism is arranged below the leaking plate, and is used to guide the bundled glass fiber direct yarn to a preset waste yarn storage area.

2. The glass fiber direct yarn detection system based on specular reflection according to claim 1 is characterized in that: The image acquisition module comprises: A closed shell, wherein the closed shell is provided with a detection port facing the leak plate, and a high-temperature resistant and highly transparent tempered glass is sealed and installed at the detection port; and A mirror imaging system comprises an industrial camera and a plane reflector, wherein the industrial camera and the plane reflector are arranged in the closed shell, the reflective surface of the plane reflector faces the detection port, the plane reflector is used to reflect the surface image of the yarn outlet side of the leak plate to the industrial camera, and the industrial camera is used to collect the surface image of the yarn outlet side of the leak plate reflected by the plane reflector to obtain the leak plate detection image.

3. The glass fiber direct yarn detection system based on specular reflection according to claim 2 is characterized in that: The image acquisition module also includes: The water mist self-cleaning system comprises a high-pressure air pipe and a high-pressure nozzle, wherein the high-pressure air pipe and the high-pressure nozzle are arranged outside the closed shell, the high-pressure nozzle is connected to the air outlet of the high-pressure air pipe, and the high-pressure nozzle is used to output a high-pressure airflow to sweep the outer surface of the high-transparency tempered glass, so as to blow away the dust and water mist that will fall on the outer surface of the high-transparency tempered glass.

4. The glass fiber direct yarn detection system based on specular reflection according to claim 3 is characterized in that: The image acquisition module also includes: A positive pressure cooling system includes an air inlet nozzle arranged on a side panel on one side of the closed shell and an exhaust fan arranged on a side panel on the other side of the closed shell opposite to the side panel on the side where the air inlet nozzle is located. The positive pressure cooling system is used to cool the industrial camera.

5. The glass fiber direct yarn detection system based on specular reflection according to claim 1, characterized in that: The waste yarn collecting mechanism comprises: A converging gripper, comprising two clamping jaws arranged opposite to each other; A first driving assembly is connected to the two clamping jaws of the converging gripper, and the first driving assembly is used to drive the two clamping jaws of the converging gripper to move closer to or away from each other, so as to close or open the converging gripper; The second driving assembly is drivingly connected to the first driving assembly, and the second driving assembly is used to drive the gathering gripper on the first driving assembly to approach or move away from the glass fiber direct yarn under the leaking plate.

6. The glass fiber direct yarn detection system based on specular reflection according to any one of claims 1 to 5, characterized in that: The yarn hole detection processing is performed on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data including: The position of the leaking board in the leaking board detection image is identified and located by a template matching algorithm, and the image area corresponding to the leaking board in the leaking board detection image is extracted to obtain a leaking board image; In combination with the template size, adaptively scaling the leak plate image to make it consistent with the template size; Segmenting the leak plate image into multiple regions to obtain multiple leak plate region images; Perform threshold segmentation on each of the leak plate area images to obtain a hole area image and a non-hole area image corresponding to each of the leak plate area images; Using an edge detection algorithm to extract edge contour information of holes in the hole area images corresponding to each of the leak plate area images; According to the extracted edge contour information, a circular hole fitting algorithm is used to perform circular hole fitting on the edge contour of the hole, and a hole area image after circular hole fitting is obtained; Calculate the number and diameter of circular holes in the corresponding leak plate region image based on the hole region image after circular hole fitting; According to the number and diameter of the circular holes in the leak plate area image, it is judged whether there is hole blockage in the leak plate area corresponding to the leak plate area image, and the visual detection result data is obtained.

7. The glass fiber direct yarn detection system based on specular reflection according to claim 6, characterized in that: Also includes: A database, used to store the visual inspection result data; as well as A data analysis module is used to analyze the visual inspection result data within a preset time period, calculate the CPK index of the glass fiber direct yarn production equipment and monitor the production quality of the glass fiber direct yarn.

8. The glass fiber direct yarn detection system based on specular reflection according to claim 7, characterized in that: The performing of data analysis on the visual inspection result data within a preset period of time to calculate the CPK index of the glass fiber direct yarn production equipment comprises: Through the time series analysis method, the average value and standard deviation of the number of circular holes in each leak plate area image in the visual inspection result data within a preset time period are analyzed, and the CPK index of the glass fiber direct yarn production equipment is calculated based on the preset CPK calculation formula.

9. The glass fiber direct yarn detection system based on specular reflection according to claim 7, characterized in that: The data analysis of the visual inspection result data within a preset time period to monitor the production quality of the glass fiber direct yarn includes: Compare and judge the circular hole quantity detection value and circular hole diameter detection value of each leak plate area image in the visual inspection result data within a preset time period with the corresponding standard value, analyze the current production status of the glass fiber direct yarn, and obtain the production status analysis result of each leak plate area; The relationship model between the number of holes detected, the diameter of holes detected and the quality of glass fiber direct yarn products is determined by time series analysis based on the number of holes detected, the diameter of holes detected and the production status analysis results of each leak plate area. The relationship model is trained using a grey wolf optimization algorithm to obtain a production quality monitoring model; The quality of glass fiber direct yarn products is monitored based on the production quality monitoring model.

10. A detection method for a glass fiber direct yarn detection system based on specular reflection according to any one of claims 1 to 9, characterized in that: The steps include: S1, the image acquisition module collects the surface image of the yarn outlet side of the leak plate in the working state in real time to obtain the leak plate detection image; S2, the image processing module performs yarn outlet hole detection processing on the leak plate detection image according to a preset image processing algorithm to obtain visual detection result data, wherein the visual detection result data is used to indicate whether the yarn outlet hole of the leak plate is blocked; S3, the process switching module switches the glass fiber direct yarn production equipment into the corresponding production process according to the visual inspection result data, wherein the production process includes a waste yarn processing process and a normal process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate has a clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the waste yarn processing process, when the visual inspection result data indicates that the yarn outlet hole of the leak plate has no clogged hole, the process switching module switches the glass fiber direct yarn production equipment into the normal process; wherein, When the process switching module switches the glass fiber direct yarn production equipment to enter the waste yarn processing process, the waste yarn gathering mechanism gathers the glass fiber direct yarn under the leak plate into a bundle, and the waste yarn guiding mechanism guides the gathered glass fiber direct yarn to the preset waste yarn storage area.

Images