Flatness detection system and method based on high-toughness PVC guardrail

Abstract

The invention relates to the technical field of guardrail flatness detection, in particular to a flatness detection system and method based on a high-toughness PVC guardrail, and the system comprises lower computer equipment and an upper computer analysis system: the lower computer equipment comprises a frame, and the frame is provided with three electric push rods; a coating device and an ink wiping strip are installed at the output ends of the left electric push rod and the right electric push rod correspondingly, the coating device comprises an ink bag and an ink rod, and two scraping strips inclined by 45 degrees are installed at the output end of the middle electric push rod through telescopic rods; an image capturing device is installed on the side, close to the ink wiping strip, of the frame. In the scheme, through physical marking design of lower computer equipment, intelligent analysis and automatic classification design of an upper computer system and real-time linkage of an upper computer and a lower computer, accurate marking, intelligent analysis and automatic classification of the concave-convex defects on the surface of the high-toughness PVC guardrail are achieved, the detection efficiency and accuracy are improved, and the detection efficiency is improved. And full-process closed-loop automation from guardrail feeding to classified storage is formed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of guardrail detection, and in particular relates to a flatness detection system and method based on high-toughness PVC guardrails. BACKGROUND

[0002] The high-toughness PVC guardrail is a guardrail product with high flexibility and impact resistance, which is made of polyvinyl chloride (PVC) as the main raw material and added with toughening agent and other components. It is commonly used for isolation and protection in places such as roadsides, parks, and communities, and has good protection function and can adapt to certain deformation without easy breakage.

[0003] The flatness detection is to ensure that the surface of the guardrail is smooth and has no obvious concave-convex defects, which not only relates to the appearance quality of the guardrail, but also affects its service life (such as easy wear at convex parts and easy accumulation of debris at concave parts leading to corrosion) and overall stability after installation.

[0004] The traditional detection system has many shortcomings: on the one hand, the detection precision is insufficient, and it is difficult to accurately identify subtle concave-convex defects, especially for high-toughness PVC guardrails which may have slight deformation, and it is easy to miss detection; on the other hand, the detection efficiency is low, and it mainly relies on manual visual inspection or semi-automatic equipment, which not only is slow, but also is greatly affected by human factors, and the judgment standard is not unified, which cannot meet the needs of large-scale production.

[0005] Therefore, the present application proposes a flatness detection system and method based on high-toughness PVC guardrails, which realizes accurate marking, intelligent analysis and automatic classification of concave-convex defects on the surface of high-toughness PVC guardrails through physical marker design of lower computer equipment, intelligent analysis and automatic classification design of upper computer system, and real-time linkage of upper and lower computers, forms a full-process closed-loop automation from guardrail feeding to classification storage, and improves the detection efficiency and accuracy. SUMMARY

[0006] The technical problems solved are insufficient precision, difficulty in identifying subtle concave-convex defects, and low efficiency.

[0007] In view of the deficiencies in the prior art, the present application provides a flatness detection system and method based on high-toughness PVC guardrails, thereby solving the technical problems mentioned in the background art.

[0008] To achieve the above purpose, the present application is realized by the following technical scheme:

[0009] A flatness detection system based on high-toughness PVC guardrails, comprising a lower computer equipment and an upper computer analysis system:

[0010] The lower machine device includes a rack, on which three electric push rods are installed. The output ends of the left and right electric push rods are respectively installed with a coating device and an ink wiping strip, the coating device including an ink sac and an ink stick, and the output end of the middle electric push rod is equipped with two scraping strips inclined at 45 degrees through a telescopic rod; an imaging device is installed on the side of the rack close to the ink wiping strip, and three conveyor belts are provided on the lower side of the rack, corresponding to the coating, ink scraping and ink wiping, and sorting areas respectively;

[0011] The ink stick, scraper and wiper of the coating equipment are designed so that the surface contacting the guardrail is conformed to the shape of the guardrail surface.

[0012] The host computer analysis system includes an image acquisition unit, an image analysis unit and a sorting control unit. The image analysis unit includes three processing modules: an image preprocessing module, a defect recognition and classification module, and a defect level determination module.

[0013] In one possible implementation, the telescopic rod consists of a sleeve rod, a sliding rod and a spring. The sliding rod is slidably nested inside the sleeve rod, and the two ends of the spring are respectively connected to the top of the inner wall of the sleeve rod and the top of the sliding rod. The scraper can adaptively fit the surface of the guardrail through elastic deformation.

[0014] In one possible implementation, the ink bag of the coating device contains water-based environmentally friendly ink, which uses water as a solvent and contains acrylic resin components. The ink stick is made of a porous elastic material, which can quantitatively absorb ink and form a uniform coating under 8N pressure.

[0015] In one possible implementation, the three conveyor belts are independently driven segmented structures, with the distance between the left conveyor belt and the middle conveyor belt being ≥5cm. The left and middle conveyor belts run at a synchronized speed of 0.6m / s, and the right conveyor belt can be steplessly adjusted within the range of 0.4-0.8m / s through PLC control.

[0016] In one possible implementation, the image acquisition unit of the upper computer analysis system establishes real-time communication with the lower computer device through the ModbusTCP industrial protocol, can synchronously control the conveyor belt speed, electric push rod pressure and imaging device triggering timing, and receive device status data feedback from the lower computer.

[0017] In one possible implementation, the defect recognition and classification module extracts features of the ink residue area based on the preprocessed image using three basic algorithms: a connected domain analysis algorithm, a feature matching algorithm, and a geometric parameter calculation algorithm, thereby identifying the defect type and determining its location. The specific process is as follows:

[0018] Extraction of residual ink areas: Based on the color-normalized binary image (ink is black, guardrail is white), a connected domain analysis algorithm is used to identify all black areas (i.e., residual ink areas). The area, perimeter, and bounding rectangle parameters of each area are calculated.

[0019] Defect type judgment:

[0020] Bump defects: Based on the characteristic of "ink residue on both sides of the bump", the ink residue area corresponding to the bump is in the form of "symmetrical double stripes" (located on both sides of the bump), and the distance between the two stripes matches the width of the scraper. The symmetry parameters of the residual area (such as symmetry axis deviation <5%) and the stripe length are calculated to determine the defect.

[0021] Depression defect: Based on the characteristic that "the ink in the depression has not been scraped off", the ink residue area corresponding to the depression is a "single area closed form" (consistent with the shape of the depression). The residual area is tested to see if it is an independent closed area (no symmetrical stripe characteristics);

[0022] Defect location: Establish a coordinate system with the upper left corner of the guardrail as the origin. Calculate the specific location of the defect on the guardrail surface through the coordinates of the center point of the circumscribed rectangle of the residual area and mark it as "raised area (x1, y1, x2, y2)" or "recessed area (x3, y3, x4, y4)".

[0023] In one possible implementation, the defect level determination module determines the level of the identified defects according to a preset level classification standard and outputs relevant results, as follows:

[0024] Classification criteria: 3 levels are set based on the geometric parameters of the residual area:

[0025] Level 1 non-destructive: no ink residue, or the residual area is less than 0.5cm 2 , which may be caused by interference from tiny impurities and is judged to be qualified;

[0026] Level 2 repairable: The total length of the raised residual strips is less than 5cm and the width of each strip is less than 0.3cm; or the concave residual area is 0.5-2cm 2 , it is judged to be a minor defect and can be repaired;

[0027] Level 3: Unrepairable: The total length of the raised residual strips is ≥5cm or the width of a single strip is ≥0.3cm; or the area of ​​the recessed residual strips is ≥2cm 2 , determined to be a serious defect and cannot be repaired;

[0028] Automatically match grades and output results: Compare the extracted residual area parameters with the grade standards, automatically determine the grade of the guardrail, generate a defect report containing type, location, and grade, output it in JSON format, and interact with the sorting unit to trigger the corresponding sorting action.

[0029] In one possible implementation, the sorting control unit of the host computer analysis system is linked to the PLC controller of the right conveyor belt via the Profinet industrial bus, and can trigger corresponding actuators according to the 1st, 2nd, and 3rd defect levels output by the image analysis unit:

[0030] The level 1 signal triggers the first group of pneumatic push rods, with a response time of ≤0.5 seconds, which push the guide plate to guide the guardrail into the qualified area branch;

[0031] The level 2 signal triggers the second set of electric swing arms, which swing 30 degrees to guide the guardrail into the repair area branch;

[0032] The level 3 signal triggers the third set of waste pushing mechanisms to move the guardrail to the waste area;

[0033] At the same time, the unit can record the number of guardrails of each level and the inspection time data, and support docking with the production management system to achieve data traceability.

[0034] In one possible implementation, a flatness detection method based on a high-toughness PVC guardrail applied to the above-mentioned system includes the following steps:

[0035] S1. Inking and scraping: During inking, the left electric push rod drives the coating equipment downward, and the ink stick presses against the guardrail with a pressure of 8N, absorbs water-based environmentally friendly ink, and completes uniform ink coating on the left conveyor belt running at 0.6m / s; During the scraping stage, the middle electric push rod uses a spring-loaded telescopic rod to make two 45° inclined scraping strips press against the guardrail with a pressure of 10-15N. The scraping strips move with the synchronously running middle conveyor belt, scraping off the ink on the flat areas, leaving symmetrical double-strip ink marks on the raised areas, and closed ink marks on the recessed areas;

[0036] S2. Image capture: After scraping and wiping, the guardrail is transported to the imaging area. A 10-megapixel industrial camera is triggered to capture images 0.3 seconds after the scraping is completed. The image of the guardrail surface is captured in conjunction with a ring light and a macro lens. The light sensor adjusts the exposure time (5-20ms) and light source brightness in real time to ensure image clarity.

[0037] S3. Analysis: After receiving the image, the host computer system first uses Gaussian filtering to remove noise, Hough transform to correct the tilt angle, and converts it to the HSV color space. It then uses connected domain analysis to extract the parameters of the ink residue area, and identifies raised or sunken defects through feature matching. Finally, it determines the defect level based on the preset threshold and generates an analysis report containing the defect location.

[0038] S4, ink wiping: The electric push rod on the right drives the ink wiping strip to fit the guardrail surface with a pressure of 5N, and moves with the middle conveyor belt to further remove the residual ink;

[0039] S5. Sorting: The right conveyor belt diverts the guardrails to the qualified area, repair area or waste area through the corresponding actuators according to the defect level instructions output by the upper computer. The action response time is ≤0.5 seconds.

[0040] In one possible implementation, the image preprocessing in step S3 also includes gray-white standardization processing, converting the ink area to black and the guardrail area to white; the defect position marking accuracy is ±0.1 cm, and the coordinates are expressed in the format of "(x1, y1, x2, y2)"; the JSON report contains the guardrail ID, defect type, location and level information, and is sent to the sorting unit in real time via the industrial bus, triggering the actuator to complete the action in ≤0.5 seconds, and the action force can be adjusted to avoid damaging the guardrail.

[0041] Beneficial effects compared with existing technologies:

[0042] 1. This solution achieves precise physical marking of uneven defects on the guardrail surface through the combination of a 45° inclined scraper and a spring-loaded telescopic rod in the lower-level device, a segmented conveyor belt, and environmentally friendly water-based ink. The scraper adapts to the guardrail, creating symmetrical double-strip ink marks on raised areas and closed ink marks on recessed areas. The segmented conveyor belt prevents ink contamination, and the water-based ink is easy to scrape off and has high contrast, ensuring clear identification of defect morphology and providing reliable physical evidence for subsequent inspections.

[0043] 2. This solution achieves intelligent analysis and automated classification of defects through image preprocessing, multi-algorithm collaborative recognition, and grading and sorting logic within the host computer system. Image preprocessing eliminates interference, while connected domain analysis and feature matching accurately identify defect type and location. Clear grading criteria are combined with a PLC-controlled sorting actuator to rapidly complete guardrail grading, replacing manual judgment and improving analysis efficiency and accuracy.

[0044] 3. In this solution, through real-time linkage between the host and slave computers based on industrial protocols (such as synchronization of the slave computer's equipment timing control with the host computer's image analysis, and real-time interaction between inspection data and sorting instructions), closed-loop automation of the entire process, from guardrail loading to classified storage, is achieved. The slave computer precisely performs physical operations, while the host computer efficiently processes data and issues instructions. The two work together to achieve a seamless connection between inspection and sorting, significantly improving production efficiency and reducing the cost of manual intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention with reference to the accompanying drawings.

[0046] Figure 1 Schematic diagram of the overall structure of the lower computer device of the present invention;

[0047] Figure 2 This is a top view of the overall structure of the lower computer device of the present invention;

[0048] Figure 3 It is a schematic structural diagram of the coating equipment of the present invention;

[0049] Figure 4 It is a schematic diagram of the telescopic rod structure of the present invention;

[0050] Figure 5 This is a schematic diagram of ink retention in a raised defect area of ​​the present invention;

[0051] Figure 6 This is a schematic diagram of ink retention in a concave defect area of ​​the present invention;

[0052] Figure 7 This is a schematic diagram of the host computer system framework of the present invention;

[0053] Figure 8 The figure is a flow chart of the method steps of the present invention.

[0054] Legend: 1. Rack; 2. Electric push rod; 3. Coating equipment; 3-1. Ink sac; 3-2. Ink stick; 4. Ink wiper; 5. Scraper; 6. Image acquisition equipment; 7. Conveyor belt; 8. Telescopic rod; 8-1. Sleeve rod; 8-2. Sliding rod; 8-3. Spring. DETAILED DESCRIPTION

[0055] Preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention can be implemented in various forms, and therefore the present invention is not limited to the embodiments described below. In addition, in order to more clearly describe the present invention, components that are not related to the present invention will be omitted from the drawings.

[0056] The technical solution in the embodiments of the present application is to solve the problems of the above-mentioned background technology, and the overall idea is as follows:

[0057] Example 1:

[0058] Please refer to Figures 1 to 7 As shown, this embodiment introduces a flatness detection system based on high-toughness PVC guardrails. The system realizes full-process automated detection through "lower-computer equipment + upper-computer analysis system", as follows:

[0059] The lower machine device includes three electric push rods 2 installed on the frame 1, and the output ends of the left and right electric push rods 2 are respectively installed with a coating device 3 and an ink wiping strip 4. The coating device 3 includes an ink sac 3-1 and an ink stick 3-2. When the left electric push rod 2 drives the coating device 3 to move downward, the ink stick 3-2 is attached to the surface of the guardrail, and the ink stick 3-2 draws the ink inside the ink sac 3-1 and coats it on the surface of the guardrail;

[0060] The right electric push rod 2 drives the ink wiping strip 4 to move downward to fit the guardrail surface, and the ink wiping strip 4 wipes off the residual ink on the guardrail surface;

[0061] The output end of the electric push rod 2 in the middle is equipped with two scraping strips 5 through a telescopic rod 8. The two scraping strips 5 are designed to be inclined at 45 degrees. The two scraping strips 5 are used to scrape the ink on the surface of the guardrail. The 45-degree inclination angle can make the scraping strips 5 form a more reasonable contact posture with the surface of the guardrail, increase the effective contact area, and make the scraping action more in line with the principle of mechanics. When the scraping strips 5 move in contact with the guardrail, the inclination angle can guide the ink to gather in a specific direction and be removed, reducing the probability of residual ink remaining on the surface of the guardrail. In particular, for the trace amount of ink that may still exist after the scraping strips 5 are scraped, it can be wiped off more thoroughly to avoid interference with the recognition of the subsequent imaging device 6.

[0062] The telescopic rod 8 includes a sleeve rod 8-1 and a slide rod 8-2 slidably connected to the interior of the sleeve rod 8-1. A spring 8-3 is provided between the top of the slide rod 8-2 and the inner wall of the sleeve rod 8-1. The slide rod 8-2 is squeezed by the slide rod 8-2 to move downward, so that the scraper 5 is always attached to the surface of the guardrail. When scraping ink, the middle electric push rod 2 drives the telescopic rod 8 and then drives the two scraper bars 5 to stick to the surface of the guardrail. When the conveyor belt 7 drives the guardrail to move, the scraper bars 5 scrape the ink on its surface.

[0063] If there are bumps on the guardrail surface, such as Figure 5 When the scraper 5 moves on the guardrail surface, it will scrape off the ink on the guardrail surface when it moves on the flat surface of the guardrail. If it encounters a raised area, the raised area will push the scraper 5 upward, and then the ink on both sides of the raised area parallel to the scraper 5 cannot be scraped off by the scraper 5, and then ink residue will be formed; when the scraper 5 moves out of the raised area, it continues to contact the guardrail surface under its own gravity and the rebound thrust of the spring 8-3, and continues to scrape off the ink on the guardrail surface;

[0064] like Figure 6 When the scraper 5 scrapes the ink on the guardrail surface, it cannot penetrate into the concave part when encountering the concave part, and then cannot scrape the ink in the concave part, while the ink in other flat parts is scraped off;

[0065] At this point, by identifying whether there is residual ink on the guardrail surface, it is possible to determine whether the guardrail is flat, and by the shape of the residual ink, it is possible to determine whether there are convexities or concave areas and the location of abnormal areas;

[0066] In addition, the ink can be water-based environmentally friendly ink. Water-based environmentally friendly ink uses water as a solvent and is combined with a small amount of environmentally friendly resin (such as acrylic resin) to provide adhesion. Its adhesion is at a "medium to weak" level. For the flat area of ​​the guardrail, the scraper 5 is tightly attached to the surface through the pressure of the spring 8-3 of the telescopic rod 8, and the ink can be easily scraped off (because the ink does not penetrate deeply and only adheres to the surface temporarily). For the protrusions, after the scraper 5 is lifted up, the ink on both sides of the protrusion is not subjected to the pressure of the scraper 5 and can remain adhered. For the concave areas, the scraper 5 cannot penetrate deeply, and the ink in the concave areas is retained because it is not scraped.

[0067] In addition, when the guardrail is placed unevenly (such as tilted, partially tilted, etc.), the slide bar 8-2 can slide flexibly in the sleeve bar 8-1, and combined with the elastic force of the spring 8-3, the scraper 5 is always closely attached to the surface of the guardrail, avoiding the gap between the scraper 5 and the guardrail due to the skewed placement of the guardrail, ensuring the continuity and effectiveness of the ink scraping action. At the same time, the elastic force of the spring 8-3 can buffer the local pressure changes caused by the uneven placement of the guardrail, preventing the scraper 5 from being damaged by the additional force generated by the tilt of the guardrail, while reducing the impact on the conveyor belt 7 and the entire equipment, ensuring the stability of the detection process;

[0068] In addition, the right electric push rod 2 drives the ink erasing strip 4 to further remove the residual ink, and the water-soluble properties of the water-based ink enable it to be easily erased by the ink erasing strip 4;

[0069] In addition, the coloring system of water-based environmentally friendly ink is flexible and can be customized with high-contrast colors according to the color of the guardrail to meet the needs of "distinctive identification";

[0070] The identification is performed by an imaging device 6 installed on the rack 1 near the ink eraser 4 side to capture the image, and then the host computer system continues to identify and judge;

[0071] Three conveyor belts 7 are provided on the lower side of the rack 1. The left conveyor belt 7 is provided on the lower side of the coating device 3, and the middle conveyor belt 7 is provided on the lower side of the scraper strip 5 and the ink wiping strip 4. The left conveyor belt 7 is separated from the middle conveyor belt 7 to prevent excess ink from dripping onto the surface of the conveyor belt 7 when the coating device 3 is applying ink to the guardrail surface, thereby affecting the image analysis at the rear side.

[0072] The right conveyor belt 7 can be extended to a conveying device with a sorting function to classify and standardize the guardrails in different situations;

[0073] It should be noted that, due to the special shape design of the guardrail, such as the wave shape, the side of the ink stick 3-2, the scraping strip 5 and the ink wiping strip 4 of the coating device 3 in contact with the guardrail is designed to match the surface shape of the guardrail. When the guardrail is placed on the conveying belt 7, the wave shape of the guardrail is preliminarily aligned with the wave shape of the ink stick 3-2, the scraping strip 5 and the ink wiping strip 4 of the coating device 3. A slight deviation will cause the pressure generated when the electric push rod 2 pushes the coating device 3, the scraping strip 5 and the ink wiping strip 4 to move downward, which will in turn drive the guardrail to move, thereby achieving the final alignment.

[0074] The upper computer analysis system comprises an image acquisition unit, an image analysis unit and a sorting control unit.

[0075] 1. Image acquisition unit

[0076] The lower computer device linkage control is based on a preset detection process, and real-time data interaction is established with the lower computer through an industrial-level communication protocol (such as Modbus TCP) to accurately control the timing of each hardware.

[0077] Conveying belt 7 control: segmented speed adjustment is adopted, the left conveying belt 7 (coating area) is set to 0.6 m / s, the middle conveying belt 7 (ink scraping, image taking and ink wiping area) is kept synchronous with the left side, and the right sorting conveying belt 7 switches the speed (0.4-0.8 m / s) according to the sorting requirement, the position of the guardrail is positioned by the photoelectric sensor to ensure that there is no delay in the connection of actions of each station.

[0078] Electric push rod 2 control:

[0079] Left electric push rod 2: after receiving the guardrail positioning signal, the coating device 3 is driven to move downward, so that the ink stick 3-2 is attached to the guardrail with a pressure of 8N to ensure uniform coverage of the ink.

[0080] Middle electric push rod 2: the telescopic rod 8 and the scraping strip 5 are driven to move downward, and the pressure signal (maintained at 10-15N) fed back by the spring 8-3 ensures that the 45° inclined scraping strip 5 is closely attached to the guardrail and moves with the conveying belt 7 to complete the ink scraping action.

[0081] Right electric push rod 2: when the guardrail enters the ink wiping area, the ink wiping strip 4 is driven to move downward to attach to the surface with a pressure of 5N, and the residual ink is removed in cooperation with the direction of the conveying belt 7.

[0082] Image acquisition:

[0083] Image taking device 6 control: a 10 million pixel industrial camera (with a macro lens) is used, and the shooting is triggered 0.3 seconds after the ink scraping is completed (to avoid the shadow of the scraping strip 5), the fill light is turned on during shooting to ensure clear imaging of the ink residue area, and the image data is uploaded to the local storage server in real time.

[0084] Environment self-adaptive adjustment, the light sensor in the image taking device 6 can automatically adjust the exposure time (5-20 ms) and light source brightness according to the reflectivity of the guardrail, avoiding image distortion caused by the difference in the surface gloss of the PVC guardrail;

[0085] 2、Image analysis unit, based on the guardrail surface image obtained by the image taking device 6, the ink residue area is identified by algorithm processing, whether the guardrail surface has concave-convex defects is judged, the defect type (convex / concave), position and grade are determined, and accurate control basis is provided for the sorting unit:

[0086] 2.1, Image preprocessing module

[0087] Image cropping and alignment, edge detection algorithm (such as Canny operator) is used to identify the edge profile of the guardrail, the background area of the conveyor belt 7 is automatically cropped, and the complete guardrail image is reserved; the image tilt angle is corrected by Hough transform (the guardrail image may be tilted due to slight deviation of the conveyor belt 7), to ensure that the subsequent analysis is based on horizontal reference;

[0088] Color standardization, aiming at the guardrail color (such as green) and ink color (such as black, blue and other high-contrast colors), the environmental light interference is eliminated by white balance correction, and then color space conversion (RGB image to HSV space) is adopted to extract the hue (H) and saturation (S) features of the ink area, ignoring the influence of brightness (V) fluctuation, realizing "gray-white standardization" processing (i.e. uniformly converting the ink area to black and the guardrail area to white, eliminating color difference interference);

[0089] Noise filtering, Gaussian filter is used to remove random noise in the image, and morphological operation (such as erosion-dilation) is used to eliminate burrs on the edge of ink residue, to ensure clear defect area profile;

[0090] 2.2, Defect identification and classification module, this module involves three basic algorithms, namely connected domain analysis algorithm, feature matching algorithm and geometric parameter calculation algorithm;

[0091] The connected domain analysis algorithm is used to extract all black ink residue areas from the preprocessed binary image (ink residue is black and guardrail flat area is white), and calculate the area, perimeter and circumscribed rectangle of each area, to provide data basis for subsequent defect judgment; for example, when the guardrail has convexity, this algorithm can extract the ink residue strips symmetrical on both sides of the convexity, and obtain the length, width and other parameters;

[0092] The feature matching algorithm, i.e. according to the correspondence between the ink residue shape and the defect type in the file (the protrusion corresponds to the "symmetrical double strip" ink residue, the depression corresponds to the "single area closed shape" ink residue), performs feature matching on the extracted ink residue area; for example, by calculating the symmetry parameter (such as the symmetry axis deviation degree) of the residue area, it is judged whether it conforms to the "symmetrical double strip" feature of the protrusion defect; by detecting whether the residue area is an independent closed region, it is judged whether it conforms to the feature of the depression defect;

[0093] The geometric parameter calculation algorithm is used to quantify the geometric features of the ink residue area, such as calculating the total length of the protruding residue strip, the single strip width, the area of the depression residue area, etc. These parameters are important basis for defect level determination; for example, when the guardrail has a depression, the algorithm can calculate the area of the ink residue area at the depression, and then compare it with the preset level threshold to determine the defect level;

[0094] Specifically: ink residue area extraction, based on the color standardized pre-processed binary image (ink is black and guardrail is white), all black areas (i.e. ink residue area) are identified by connected component analysis algorithm, and the area, perimeter, circumscribed rectangle and other geometric parameters of each area are calculated;

[0095] For example, there are two black areas in the image: one is "parallel double strip" (width about 0.2 cm, length about 3 cm), and the other is "irregular closed area" (area about 1.2 cm²); through the connected component analysis algorithm, the geometric parameters of the two areas are extracted, i.e.: double strip area: total pixel points converted to area 0.6 cm², perimeter 6.4 cm, two strip spacing matches the width of the scraping strip 5 (preset 1 cm); closed area: pixel points converted to area 1.2 cm², perimeter 4.5 cm, edge is arc-shaped;

[0096] Defect type judgment:

[0097] Protrusion defect: according to the feature of "ink residue on both sides of the protrusion" in the file, the ink residue area corresponding to the protrusion is in the form of "symmetrical double strip" (located on both sides of the protrusion), and the spacing between the two strips matches the width of the scraping strip 5 (because the scraping strip 5 is lifted, the symmetrically distributed non-scraped areas on both sides); by calculating the symmetry parameter (such as the symmetry axis deviation degree < 5%) and the strip length (positively correlated with the length of the protrusion) of the residue area, it is determined as a protrusion defect;

[0098] For example, the aforementioned "parallel double stripes" area meets the characteristic of "ink residue on both sides of the protrusion" in the document: when the scraper 5 encounters a 1mm high protrusion on the guardrail surface, the protrusion pushes the scraper 5 upward, causing the unscratched ink on both sides of the protrusion to form symmetrically distributed stripes (similar to "ink on both sides of the protrusion remains because it is not under the pressure of the scraper 5"). According to the algorithm calculation, the deviation of the symmetry axis of the double stripes is 3% (<5%), which meets the morphological characteristics of "symmetrical double stripes", and therefore the area is determined to be a protrusion defect.

[0099] Depression defects: Based on the characteristic that the ink in the depression has not been scraped off, the ink residue area corresponding to the depression is a "single closed area" (consistent with the shape of the depression), and the area is positively correlated with the size of the depression. The residual area is detected to determine whether it is an independent closed area (without symmetrical stripe characteristics) to determine whether it is a depression defect;

[0100] For example, the aforementioned "irregular closed area" meets the characteristic of "unremoved ink in the depression" in the document: when a depression with a diameter of 0.8 cm and a depth of 0.5 mm exists on the guardrail surface, the scraper strip 5 cannot penetrate deep into the depression, resulting in ink retention within the depression, forming a closed area consistent with the depression shape (without symmetrical strip features). The algorithm detects this area as an independent closed form and therefore determines it as a depression defect.

[0101] Defect location: establish a coordinate system with the upper left corner of the guardrail as the origin. Calculate the specific location of the defect on the guardrail surface (e.g., 30 cm from the left end on the X axis and 20 cm from the front end on the Y axis) using the coordinates of the center point of the circumscribed rectangle of the residual area, and mark it as "raised area (x1, y1, x2, y2)" or "recessed area (x3, y3, x4, y4)";

[0102] For example, taking the upper left corner of the guardrail as the origin (0, 0), establish a two-dimensional coordinate system (unit: cm):

[0103] The coordinates of the upper left corner of the circumscribed rectangle of the double-strip area of ​​the raised defect are (10.5, 5.2), and the coordinates of the lower right corner are (13.5, 6.2), so it is marked as "raised area (10.5, 5.2, 13.5, 6.2)", indicating that the raised area is located within 10.5-13.5 cm from the left end and 5.2-6.2 cm from the front end of the guardrail;

[0104] The coordinates of the center point of the circumscribed rectangle of the closed area of ​​the above-mentioned concave defect are (20.3, 8.7), so it is marked as "Concave area (19.9, 8.3, 20.7, 9.1)", indicating that the concave is located within the range of 19.9-20.7 cm from the left end and 8.3-9.1 cm from the front end of the guardrail;

[0105] 2.3 Defect level determination module

[0106] The classification standard is to set n levels based on the geometric parameters of the residual area (the example uses 3 levels):

[0107] Level 1 (non-destructive): No ink residue, or the residual area is less than 0.5 cm 2 (May be due to interference from tiny impurities, judged as qualified);

[0108] Level 2 (repairable): The total length of the raised residual strips is less than 5cm and the width of each strip is less than 0.3cm; or the concave residual area is 0.5-2cm 2 , it is judged as a minor defect and can be repaired; for example, the total length of the double strips is 3cm (<5cm), and the width of a single strip is 0.2cm (<0.3cm), which meets the "Level 2 (Repairable)" standard and is therefore judged to be a repairable raised defect; the closed area is 1.2cm 2 (between 0.5-2cm 2 The defect is considered repairable because it meets the "Level 2 (repairable)" standard.

[0109] Level 3 (irreparable): The total length of the raised residual strips is ≥5cm or the width of a single strip is ≥0.3cm; or the area of ​​the recessed residual strips is ≥2cm 2 , it is judged as a serious defect and cannot be repaired; for example, if the total length of the raised strips on another guardrail is 6cm (≥5cm), it will be directly judged as "Level 3 (Irrepairable)";

[0110] (Note: The specific threshold can be adjusted according to guardrail specifications and industry standards, and the number of n can be expanded)

[0111] Automatic grade matching: Compare the extracted residual area parameters with the grade standard, automatically determine the grade of the guardrail, and generate a defect report (including type, location, and grade);

[0112] The data output and linkage module outputs analysis results in JSON format. Example:

[0113] {"Guardrail ID":"PVC20230801001",

[0114] "Defect Type": "Bump",

[0115] "Defect location": "(15.2, 8.3, 20.5, 10.1)",

[0116] "Level": "Level 2",

[0117] "Judgment Result": "Repairable"}

[0118] Linked with the sorting unit, the judgment results are sent to the sorting control unit in real time via an industrial bus (such as Profinet), triggering the sorting action of the right conveyor belt 7 (for example, level 1 products enter the qualified area, level 2 enter the repair area, and level 3 enter the waste area), thus realizing an automated closed loop of detection and sorting;

[0119] 3. The sorting control unit, based on the guardrail defect level (such as intact, repairable, non-repairable, etc.) output by the image analysis unit, automatically sorts and conveys guardrails of different levels through the right conveyor belt 7 and the supporting actuator, ensuring a closed-loop inspection-sorting process and improving production efficiency.

[0120] When the guardrail passes under the imaging device 6 and the image analysis is completed, the image analysis unit sends the defect level data (such as "level 1 - damageless" and "level 2 - repairable") to the sorting unit PLC in real time;

[0121] The PLC uses the guardrail's transit time on conveyor belt 7 (calculated based on the conveyor belt 7 speed of 0.4-0.8m / s) to match the received grade data with the guardrail that actually arrives at the to-be-sorted section (matching can be assisted by the timestamp of the guardrail edge detection);

[0122] Positioning trigger:

[0123] When the guardrail enters the right conveyor belt 7 to be sorted, the first photoelectric sensor is triggered, the PLC records the guardrail position, and starts timing;

[0124] When the guardrail reaches the entrance of the diversion section, the secondary positioning sensor detects a signal, and the PLC confirms that the guardrail is in the sorting position and is ready to perform the diversion action;

[0125] Grading and sorting execution:

[0126] According to the defect level, the PLC controls the sorting actuator actions of the corresponding group:

[0127] If it is level 1 (non-destructive): the first group of pneumatic push rods in the diversion section extend, pushing the guide plate to tilt toward the level 1 branch conveyor belt 7, and the guardrail moves with the conveyor belt 7 into the qualified area branch, and the push rods are then reset;

[0128] If it is level 2 (repairable): the second set of electric swing arms in the diversion section swings to guide the guardrail to the level 2 repair area branch, and the swing arms reset after 3 seconds;

[0129] If it is level 3 (irreparable): the third set of actuators in the diversion section will operate, pushing the guardrail into the level 3 waste area branch;

[0130] (Note: The actuator action time is ≤ 0.5 seconds to ensure that the guidance is completed before the guardrail completely passes through the diversion section. The action force can be adjusted to avoid damage to the guardrail);

[0131] Classified storage:

[0132] The guardrail entering the branch conveyor belt 7 is blocked by a limit baffle at the end. After 5-10 pieces are accumulated, the branch conveyor belt 7 automatically stops (detected by the end sensor) and restarts after being manually removed to achieve batch storage.

[0133] Example 2:

[0134] Please refer to Figure 8 As shown, this embodiment introduces a flatness detection method based on high-toughness PVC guardrail, and the method includes the following steps:

[0135] S1. Ink application and ink scraping:

[0136] S1.1, Inking: The left electric push rod 2 drives the coating device 3 downward, so that the ink stick 3-2 is pressed against the guardrail surface with a pressure of 8N. The ink stick 3-2 absorbs the water-based environmentally friendly ink (high-contrast color can be customized according to the guardrail color) in the ink bag 3-1 and evenly coats the guardrail surface. The left conveyor belt 7 drives the guardrail at a speed of 0.6m / s to complete the inking.

[0137] S1.2, ink scraping: The central electric push rod 2 drives the telescopic rod 8 and two 45° inclined scraping bars 5 to move downward. The spring 8-3 maintains a pressure of 10-15N, so that the scraping bars 5 are closely attached to the surface of the guardrail. The central conveyor belt 7 runs synchronously with the left side at a speed of 0.6m / s, driving the guardrail to move, and the scraping bars 5 scrape the ink.

[0138] Flat area of ​​guardrail: ink is completely scraped off;

[0139] Raised area: The raised area pushes up the scraper 5, and ink residue on both sides of the raised area forms a symmetrical double stripe; after the scraper 5 moves out of the raised area, it resumes contact under the force of gravity and the thrust of the spring 8-3 and continues scraping ink;

[0140] Depression: The scraper 5 cannot penetrate into the depression, and the ink is retained in the depression to form a closed area.

[0141] S2. Image acquisition:

[0142] The imaging device 6 (a 10-megapixel industrial camera with a macro lens) is installed near the ink-wiping strip 4. It triggers the capture 0.3 seconds after the ink is wiped off, avoiding the shadow cast by the scraping strip 5. During the capture, the fill light is turned on, and the built-in light sensor automatically adjusts the exposure time (5-20ms) and light source brightness based on the reflectivity of the guardrail to ensure clear imaging of the ink residue area. The image data is uploaded to the host computer system in real time.

[0143] S3. Analysis:

[0144] S3.1 Image processing:

[0145] Image cropping and alignment: Use the Canny operator to identify the edge of the guardrail and crop the background of the conveyor belt 7; use the Hough transform to correct the image tilt angle to ensure that the analysis is based on a horizontal reference;

[0146] Color standardization: White balance is used to eliminate ambient light interference, converting the RGB image to HSV space, extracting the hue (H) and saturation (S) characteristics of the ink area, ignoring brightness (V) fluctuations, and converting the ink area to black and the guardrail area to white to achieve gray-white standardization;

[0147] Noise filtering: Gaussian filtering is used to remove random noise, and corrosion-dilation morphological operations are combined to eliminate ink residual edge burrs, making the outline of the defect area clear;

[0148] S3.2 Defect identification and classification:

[0149] Ink residue area extraction: Based on the binary image, all black residual areas are identified through the connected domain analysis algorithm, and the geometric parameters such as area, perimeter, and circumscribed rectangle of each area are calculated;

[0150] Defect type judgment:

[0151] Bump defect: The residual area is in the form of "symmetrical double stripes", the distance between the two stripes matches the width of the scraper strip 5, and the deviation of the symmetry axis is less than 5%, which is judged as a bump;

[0152] Concave defect: The residual area is an independent closed area without symmetrical stripe features and is judged as a concave;

[0153] Defect location: Establish a coordinate system with the upper left corner of the guardrail as the origin, and mark the defect location (such as "convex area (x1, y1, x2, y2)" and "concave area (x3, y3, x4, y4)") through the coordinates of the center point of the circumscribed rectangle of the residual area;

[0154] S3.3 Defect grade determination:

[0155] Level 1 (non-destructive): No ink residue, or the residual area is less than 0.5 cm 2 (determined to be qualified);

[0156] Level 2 (repairable): The total length of the raised residual strips is less than 5 cm and the width of each strip is less than 0.3 cm, or the concave residual area is 0.5-2 cm 2 (determined to be a minor defect);

[0157] Level 3 (irreparable): The total length of the raised residual strips is ≥5cm or the width of a single strip is ≥0.3cm, or the area of ​​the depressed residual strips is ≥2cm² (determined as a serious defect);

[0158] Generate a JSON format report containing defect type, location, and level;

[0159] S4, ink wiping: The right electric push rod 2 drives the ink wiping strip 4 to press against the guardrail surface with a pressure of 5N, and moves along with the middle conveyor belt 7 to further remove the residual ink (using the water-soluble property of water-based ink);

[0160] S5. Sorting:

[0161] Data matching: The right conveyor belt 7 receives the analyzed guardrail. The PLC calculates the transmission time based on the conveyor belt 7 speed (0.4-0.8m / s) and matches the defect level data with the guardrail (combined with the guardrail edge detection timestamp).

[0162] Positioning trigger: The guardrail enters the sorting section of the right conveyor belt 7, triggering the first photoelectric sensor; when it reaches the entrance of the diversion section, the secondary positioning sensor confirms the position and prepares for sorting;

[0163] Tiered Implementation:

[0164] Level 1 (non-destructive): The first set of pneumatic push rods in the diversion section extends, pushing the guide plate to guide the guardrail into the qualified area branch conveyor belt 7;

[0165] Level 2 (repairable): The second set of electric swing arms swings to guide the guardrail to the repair area branch;

[0166] Level 3 (non-repairable): The third set of actuators operates, pushing the guardrail into the waste area branch; the actuator action time is ≤ 0.5 seconds, and the force is adjustable;

[0167] Classification storage: The end limit baffle of branch conveyor belt 7 blocks the guardrail and automatically stops after accumulating 5-10 pieces, and restarts after being manually taken away to realize batch storage.

[0168] Finally, it should be noted that the above embodiments are merely examples for the purpose of illustrating the present invention and are not intended to limit the embodiments. Those skilled in the art will readily appreciate that other variations or modifications based on the above description are possible. It is not necessary and impossible to provide an exhaustive list of all embodiments. However, obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A flatness detection system based on high-toughness PVC guardrail, including a lower computer device and a host computer analysis system, characterized by: The lower machine device comprises a rack (1), three electric push rods (2) are mounted on the rack (1), a coating device (3) and an ink wiping strip (4) are mounted on the output ends of the left and right electric push rods (2), respectively, the coating device (3) comprises an ink bag (3-1) and an ink stick (3-2), and two scraping strips (5) inclined at 45 degrees are mounted on the output end of the middle electric push rod (2) via a telescopic rod (8); an imaging device (6) is mounted on the side of the rack (1) close to the ink wiping strip (4), and three conveyor belts (7) are arranged on the lower side of the rack (1), corresponding to the coating, ink scraping and ink wiping, and sorting areas respectively; The ink stick (3-2), scraper strip (5), and ink wiping strip (4) of the coating device (3) are designed so that the sides in contact with the guardrail are all designed to fit the shape of the guardrail surface; The host computer analysis system includes an image acquisition unit, an image analysis unit and a sorting control unit. The image analysis unit includes three processing modules: an image preprocessing module, a defect recognition and classification module, and a defect level determination module.

2. A flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The telescopic rod (8) is composed of a sleeve rod (8-1), a slide rod (8-2) and a spring (8-3). The slide rod (8-2) is slidably nested inside the sleeve rod (8-1). The two ends of the spring (8-3) are respectively connected to the top of the inner wall of the sleeve rod (8-1) and the top of the slide rod (8-2). The scraper strip (5) can be adaptively fitted to the guardrail surface through elastic deformation.

3. A flatness detection system based on high-toughness PVC guardrail according to claim 2, characterized in that: The ink bag (3-1) of the coating device (3) is equipped with a water-based environmentally friendly ink, which uses water as a solvent and contains an acrylic resin component. The ink stick (3-2) is made of a porous elastic material and can quantitatively absorb the ink and form a uniform coating under a pressure of 8N.

4. A flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The three conveyor belts (7) are independently driven segmented structures. The distance between the left conveyor belt and the middle conveyor belt is ≥5cm. The running speed of the left and middle conveyor belts is synchronized at 0.6m / s. The right conveyor belt can be steplessly adjusted in the range of 0.4-0.8m / s through PLC control.

5. The flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The image acquisition unit of the host computer analysis system establishes real-time communication with the slave computer device through the ModbusTCP industrial protocol, can synchronously control the conveyor belt speed, electric push rod pressure and imaging device triggering timing, and receive device status data fed back by the slave computer.

6. A flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The defect recognition and classification module extracts the features of the ink residue area based on the preprocessed image using three basic algorithms: connected domain analysis algorithm, feature matching algorithm, and geometric parameter calculation algorithm, thereby identifying the defect type and determining its location. The specific process is as follows: Extraction of ink residue areas: Based on the color-normalized binary image, all black areas are identified using the connected domain analysis algorithm, and the area, perimeter, and bounding rectangle parameters of each area are calculated. Defect type judgment: Bump defects: Based on the characteristic of "ink residue on both sides of the bump," the ink residue area corresponding to the bump is in the form of "symmetrical double stripes," and the distance between the two stripes matches the width of the scraper. The symmetry parameters of the residual area and the stripe length are calculated to determine the defect. Depression defect: Based on the characteristic that the ink in the depression is not scraped off, the ink residue area corresponding to the depression is a "single closed area". The determination is made by testing whether the residual area is an independent closed area; Defect location: Establish a coordinate system with the upper left corner of the guardrail as the origin, calculate the specific location of the defect on the guardrail surface through the coordinates of the center point of the circumscribed rectangle of the residual area, and mark it.

7. The flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The defect grade determination module determines the grade of the identified defects according to the preset grade classification standard and outputs the relevant results. The specific contents are as follows: Classification criteria: 3 levels are set based on the geometric parameters of the residual area: Level 1 non-destructive: no ink residue, or the residual area is less than 0.5cm 2 , which may be caused by interference from tiny impurities and is judged to be qualified; Level 2 repairable: The total length of the raised residual strips is less than 5cm and the width of each strip is less than 0.3cm; or the concave residual area is 0.5-2cm 2 , it is judged to be a minor defect and can be repaired; Level 3: Unrepairable: The total length of the raised residual strips is ≥5cm or the width of a single strip is ≥0.3cm; or the area of ​​the recessed residual strips is ≥2cm 2 , determined to be a serious defect and cannot be repaired; Automatically match grades and output results: Compare the extracted residual area parameters with the grade standards, automatically determine the grade of the guardrail, generate a defect report containing type, location, and grade, output it in JSON format, and interact with the sorting unit to trigger the corresponding sorting action.

8. The flatness detection system based on high-toughness PVC guardrail according to claim 1, characterized in that: The sorting control unit of the host computer analysis system is linked to the PLC controller of the right conveyor belt via the Profinet industrial bus, and can trigger the corresponding actuator according to the 1, 2, and 3 defect levels output by the image analysis unit: The level 1 signal triggers the first group of pneumatic push rods, with a response time of ≤0.5 seconds, which push the guide plate to guide the guardrail into the qualified area branch; The level 2 signal triggers the second set of electric swing arms, which swing 30 degrees to guide the guardrail into the repair area branch; The level 3 signal triggers the third set of waste pushing mechanisms to move the guardrail to the waste area; At the same time, the unit can record the number of guardrails of each level and the inspection time data, and support docking with the production management system to achieve data traceability.

9. A flatness detection method based on a high-toughness PVC guardrail applied to the system according to any one of claims 1 to 8, characterized in that: The method comprises the following steps: S1, ink application and ink scraping: During ink application, the left electric push rod (2) drives the coating device downward, and the ink stick (3-2) is pressed against the guardrail with a pressure of 8N, absorbs the water-based environmentally friendly ink, and completes uniform ink application on the left conveyor belt (7) running at 0.6m / s; During the ink scraping stage, the middle electric push rod (2) uses the telescopic rod (8) with a spring (8-3) to make two 45° inclined scraping strips (5) press against the guardrail with a pressure of 10-15N, and move with the synchronously running middle conveyor belt (7), and the ink is scraped off on the flat part, leaving symmetrical double-strip ink marks on the convex part and closed ink marks on the concave part; S2. Image capture: After being inked and scraped, the guardrail is transported to the imaging area. A 10-megapixel industrial camera is triggered to capture images 0.3 seconds after the scraping is completed. The camera uses a ring light and a macro lens to capture images of the guardrail surface. The light sensor adjusts the exposure time (5-20ms) and light source brightness in real time to ensure image clarity. S3. Analysis: After receiving the image, the host computer system first uses Gaussian filtering to remove noise, Hough transform to correct the tilt angle, and converts it to the HSV color space. It then uses connected domain analysis to extract the parameters of the ink residue area, and identifies raised or sunken defects through feature matching. Finally, it determines the defect level based on the preset threshold and generates an analysis report containing the defect location. S4, ink wiping: the right electric push rod (2) drives the ink wiping strip (4) to adhere to the guardrail surface with a pressure of 5N, and moves with the middle conveyor belt to further remove the residual ink; S5. Sorting: The right conveyor belt (7) diverts the guardrails to the qualified area, repair area or waste area through the corresponding actuator according to the defect level instruction output by the host computer, and the action response time is ≤0.5 seconds.

10. A method for detecting flatness of a high-toughness PVC guardrail according to claim 9, characterized in that: Image preprocessing in step S3 also includes grayscale standardization, converting ink areas to black and guardrail areas to white. Defect locations are marked with an accuracy of ±0.1 cm, with coordinates expressed in the format "(x1, y1, x2, y2)". A JSON report containing the guardrail ID, defect type, location, and level is sent to the sorting unit in real time via the industrial bus, triggering the actuator to complete the action in ≤0.5 seconds, with adjustable force to avoid damage to the guardrail.

Images