Defect detection device in glass bottle production process flow
By designing an automated glass bottle defect detection device and combining image processing algorithms, the problem of low manual detection efficiency and poor reliability is solved, efficient and accurate defect detection is achieved, and the quality control capability of glass bottle production is improved.
Patent Information
- Application Number
- CN202422287783.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2025-07-29
- Estimated Expiration
- 2034-09-19
AI Technical Summary
In the production process of existing glass bottles, defect detection mainly relies on manual testing, and there are problems of low efficiency, poor reliability and low intelligence, which cannot meet the needs of high-quality production.
A defect detection device in the production process of glass bottles is designed, using a conveyor rack, detection mechanism, rotary lifting mechanism and light source module, combined with an image processing algorithm to realize automated defect detection, including the detection of white bottles, glazed coating and decal paper.
It realizes efficient and accurate defect detection, improves detection rate, avoids omissions, provides accurate quality data, and provides an effective basis for quality control in the production process of glass bottles.
Smart Images
Figure CN223166632U_ABST
Abstract
Description
Technical Field
[0001] The utility model relates to the technical field of glass bottle defect detection devices, and in particular to a device for defect detection in the production process of glass bottles. Background Art
[0002] During the production process of a glass bottle production line, product inspection is carried out, including defect detection procedures for inspecting white bottles, glazing, and decal paper pasting. Each production line produces different types of wine bottles, with a total of up to hundreds of types. Among them, inspecting white bottles refers to the state when the glass is just produced, and the bottle body is made of transparent glass, and defects throughout the body need to be detected. It is known that weight, cracks, air bubbles, etc. need to be detected. For glazing inspection, color difference and defect detection are required, including but not limited to whether there is missed glazing on the bottle body and whether the pattern is defective. For decal paper pasting inspection, it includes pattern defects, whether it is pasted correctly, air bubbles, cracks, etc. These defects not only affect the aesthetics of the product but also pose potential safety hazards.
[0003] Traditional methods for detecting glass bottle defects mainly rely on manual inspection. Manual inspection cannot comprehensively detect defects at the bottle mouth, indirectly leading to an increase in production costs. Moreover, some cracks can only be seen under certain light reflection conditions. Due to individual visual differences, detecting glass bottle defects by the naked eye will affect the detection effect. When there are operation errors, it is easy to cause damage to the detection device. In addition, in the existing detection of glass bottles, the types of glass bottle defects cannot be obtained more accurately, which cannot provide positive reference significance for the production of glass bottles, and the degree of intelligence in the existing detection of glass bottles is low. With the improvement of product quality requirements, the requirements for the yield rate and finished product rate of glass bottles are getting higher and higher, and real-time detection of the glass bottle production process is also required, with strict quality control over the produced glass bottles to ensure that the quality passes.
[0004] The existing methods for detecting surface defects of glass bottles mainly rely on manual measurement, which is slow and inefficient. At the same time, the manual method requires the inspectors to have certain professional skills. This leads to subjectivity in manual detection and the lack of reliability of the detection results. Prolonged use of the eyes is likely to cause eye fatigue, resulting in poor detection effects. With the development of processing technology and the improvement of requirements, due to the continuous increase in production speed, manual detection has become increasingly difficult and cannot guarantee the quality of glass bottle production and processing. Summary of the Utility Model
[0005] In order to solve the deficiencies in the detection during the production process of existing glass bottles, a glass bottle defect detection device is provided, which can automatically detect the defects of white bottles, glazed bottles, and decaled bottles. It can better meet the shooting requirements and present the best effects; it can better highlight the defects; it can comprehensively detect the surface of the glass bottle, greatly improving the detection rate; it can complete rapid automation to replace manual labor to automatically detect the glass bottles to be tested; the present utility model provides a device for defect detection in the production process of glass bottles.
[0006] The device for defect detection in the production process of glass bottles provided by the present utility model adopts the following technical solutions: It includes a conveyor frame. On one side of the conveyor frame, a main support frame is vertically provided. On the main support frame, a first support frame and a second support frame perpendicular to each other are respectively provided. The first support frame is arranged on one side of the conveyor frame and along the conveying direction, and the second support frame is located above the conveyor frame and perpendicular to the conveying direction; a detection mechanism is provided on the first support frame, and a rotary lifting mechanism is provided on the second support frame.
[0007] As a preferred implementation manner, a conveyor belt is installed on the conveyor frame, and a guiding mechanism and a bottle blank body are provided on the conveyor belt.
[0008] As a preferred implementation manner, the detection mechanism includes a camera and a mounting plate. The mounting plate is arranged on the first support frame, and the camera is provided on the mounting plate.
[0009] As a preferred implementation manner, the rotary lifting mechanism includes a lifting module, a rotary module, and a clamping and placing module.
[0010] As a preferred implementation manner, a light source module is further provided on one side of the conveyor frame, and the light source module is arranged opposite to the detection mechanism.
[0011] As a preferred implementation manner, a light source module is further provided on one side of the conveyor frame, and the light source module and the detection mechanism are arranged side by side on the first support frame.
[0012] As a preferred implementation manner, the camera is electrically connected to a controller, and the controller is electrically connected to the rotary lifting mechanism.
[0013] As a preferred implementation manner, the light source module includes a strip light source, a strip light source rotary support plate, and a strip light source fixing plate. The strip light source rotary support plate is fixedly arranged on the first support frame through the strip light source fixing plate.
[0014] To sum up, the present utility model has the following beneficial technical effects:
[0015] In the present utility model, a bottle preform is detected by a detection mechanism, which transmits a signal to a controller. The controller controls a rotary lifting mechanism to clamp and rotate the bottle preform, and perform real-time image acquisition and defect detection. Whether there is a defect is detected, and if a defect is found, it is removed in real time. If there is no defect, the detection of the next glass bottle is carried out. This can greatly improve the detection rate, avoid omission and achieve accurate measurement, better meet the shooting requirements and present the best effect, and can better highlight the defects. The accurate data collected provides an effective basis for users to judge the overall quality data in the production process of glass bottles. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 is a schematic structural diagram of a device for defect detection in the production process flow of glass bottles of the present utility model;
[0017] Figure 2 is the present utility model Figure 1 a schematic structural diagram of A therein;
[0018] Figure 3 is the present utility model Figure 1 a schematic structural diagram of B therein;
[0019] Figure 4 Schematic structural diagram of the rotary lifting mechanism of the present utility model.
[0020] Figure 5 Top view of the device for defect detection in the production process flow of glass bottles of the present utility model.
[0021] Description of reference numerals: 1, conveyor frame; 101, conveyor belt; 2, main support frame; 3, first support frame; 4, second support frame; 5, detection mechanism; 501, camera; 502, mounting plate; 6, rotary lifting mechanism; 601, lifting module; 602, rotating module; 603, clamping and releasing module; 7, guiding mechanism; 8, bottle preform body; 9, light source module; 10, strip light source module. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present utility model with reference to the accompanying drawings in the embodiments of the present utility model. Obviously, the described embodiments are only a part of the embodiments of the present utility model, rather than all of the embodiments. Based on the embodiments of the present utility model, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present utility model.
[0023] Embodiment 1
[0024] As Figure 1 - Figure 2 and Figure 5As shown, it is the inspection of white bottles, which refers to the state when the glass is just produced. The bottle body is made of transparent glass, and the whole body needs to be inspected for defects. It is known that the weight, cracks, air bubbles, etc. need to be inspected. The present utility model provides a technical solution: a device for defect inspection in the production process of glass bottles, including: a conveyor rack 1, a main support frame 2 is vertically arranged on one side of the conveyor rack 1, and a first support frame 3 and a second support frame 4 perpendicular to each other are respectively arranged on the main support frame 2. The first support frame 3 is arranged on one side of the conveyor rack 1 and along the conveying direction, and the second support frame 4 is located above the conveyor rack 1 and perpendicular to the conveying direction; a detection mechanism 5 is arranged on the first support frame 3, and a rotary lifting mechanism 6 is arranged on the second support frame 4.
[0025] In this embodiment, a conveyor belt 101 is installed on the conveyor rack 1, and a guiding mechanism 7 is arranged on the conveyor belt 101. By arranging the guiding mechanism 7, the transportation track of the bottle embryo body 8 can be maintained, which is convenient for the bottle embryo body 8 to reach the designated position and is convenient for clamping; by arranging the detection mechanism 5, the detection mechanism 5 includes a camera 501 and a mounting plate 502. The mounting plate is arranged on the first support frame 3, and the camera 501 is arranged on the mounting plate. The mounting plate 502 can provide stable adjustment on the first support frame 3. The camera 501 is used for taking pictures of white bottle defects. One picture can be generated by taking one picture. By the way of rotating 90 degrees to obtain the whole body, it is necessary to take pictures of the whole surface one by one. By the way of rotating the angle first and then taking pictures, the production speed of the production line and the detection speed are guaranteed; the camera 501 is electrically connected to the controller, and the controller is electrically connected to the rotary lifting mechanism 6.
[0026] As Figure 2 and Figure 4 As shown, the rotary lifting mechanism 6 includes a lifting module 601, a rotary module 602 and a clamping and releasing module 603; the lifting module 601 is fixed on the second support frame 4, the rotary module 602 is fixedly arranged on one side of the lifting module 601, and the clamping and releasing module 603 is fixedly arranged at the bottom of the rotary module 602.
[0027] In this embodiment, the rotary lifting mechanism 6 provides functions such as lifting, rotating, clamping and releasing for the shooting of glass bottles; a light source module 9 is also arranged on one side of the conveyor rack 1. The light source module 9 is arranged opposite to the detection mechanism 5. The light source module 9 is the active lighting unit of the system. The backlight can provide uniform illumination, so that the surface of the object to be detected is evenly illuminated. The backlight is located behind the object to be detected, and can effectively eliminate shadows and reflections; by placing the light source in the opposite direction to the camera, the foreground and background of the object to be detected can be clearly separated, and the interference factors in the image can be reduced.
[0028] Working principle:
[0029] For the collected white bottle images, a reasonable detection and rapid analysis are carried out using defect and anomaly recognition algorithms. The backlight illumination form is used in combination with the image preprocessing algorithm to obtain a binary image. The same glass bottle is photographed at two perpendicular angles, that is, one photo is taken first, and then the rotating device is used to rotate 90 degrees and another photo is taken. The defect recognition algorithm is used to quickly identify and process bubbles, cracks, and other impurities in the bottle body image, and real-time feedback is carried out.
[0030] Embodiment 2
[0031] As Figure 1 and Figure 3 - Figure 5 shown, for glaze detection, color difference detection and defect detection are required, including but not limited to whether there is missed glazing on the bottle body, whether the pattern is defective, etc. Detect the decal paper, including pattern defects, whether it is pasted correctly, bubbles, cracks, etc. The difference between this embodiment and Embodiment 1 is that a strip light source module 10 is provided on one side of the conveyor rack 1, and the strip light source module 10 and the detection mechanism 5 are arranged side by side on the first support frame 3.
[0032] In this embodiment, the strip light source module 10 includes a strip light source, a strip light source rotating support plate and a strip light source fixing plate. The strip light source rotating support plate is fixedly arranged on the first support frame 3 through the strip light source fixing plate, providing high-brightness, uniform and well-directional illumination, which is particularly suitable for occasions that require precise illumination imaging.
[0033] Since the glazed glass bottle does not have sufficient light transmittance, the method of obtaining the whole body by using a single angle and a 90-degree rotation once can no longer be used. It is necessary to take pictures of the entire surface one by one. By using the method of rotating the angle first and then taking pictures, the production line speed and detection speed are guaranteed. A line array camera is used in combination with a rotating device to quickly rotate one circle to realize the rapid image acquisition and recognition of the bottle body.
[0034] Working principle:
[0035] For glaze recognition, a line array camera is used to clearly image the surface of the glass bottle rotated by the rotating device according to the set imaging area. First, image preprocessing is carried out on the obtained image, including but not limited to denoising, morphology, and feature recognition, to obtain the feature information to be used for targeted recognition. First, color recognition is carried out, mainly to recognize whether the overall color distribution in the image is uniform. The color recognition algorithm is used to give real-time feedback on the areas with inconsistent colors; when there is no problem with the color, the defect recognition algorithm is used to identify the defects on the bottle body, and the defects are removed in real time. If there are no defects, the detection of the next glass bottle is carried out.
[0036] For decal detection, the decal area is obtained through image preprocessing. First, the position recognition algorithm is used to determine whether the decal position meets the requirements. If the decal is pasted crookedly, an alarm is given in a timely manner. When the decal position is appropriate, the defect recognition algorithm, including but not limited to the template matching algorithm and the black and white block area calculation algorithm, is used to identify whether there are defects in the font and pattern of the decal itself, whether there are air bubbles and cracks. When there are defects, they are removed in real time.
[0037] The installation of the guiding mechanism 7 not described in detail in this specification belongs to the prior art well known to those skilled in the art.
[0038] Finally, it should be noted that the above are only preferred embodiments of the present invention, and the present invention is not limited to other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still belong to the protection scope of the technical solution of the present invention.
Claims
1. An apparatus for defect detection in the production process of glass bottles, characterized in that: It includes a conveying rack (1), on one side of which a main support frame (2) is vertically arranged. On the main support frame (2), a first support frame (3) and a second support frame (4) perpendicular to each other are respectively arranged. The first support frame (3) is arranged on one side of the conveying rack (1) and along the conveying direction, and the second support frame (4) is located above the conveying rack (1) and perpendicular to the conveying direction. A detection mechanism (5) is arranged on the first support frame (3), and a rotary lifting mechanism (6) is arranged on the second support frame (4).
2. The device for defect detection in the glass bottle production process according to claim 1, characterized in that: A conveyor belt (101) is installed on the conveying rack (1), and a guiding mechanism (7) and a preform body (8) are arranged on the conveyor belt (101).
3. The device for defect detection in the glass bottle production process according to claim 1, wherein: The detection mechanism (5) includes a camera (501) and a mounting plate (502). The mounting plate is arranged on the first support frame (3), and the camera (501) is arranged on the mounting plate.
4. The device for defect detection in the glass bottle production process according to claim 1, characterized in that: The rotary lifting mechanism (6) includes a lifting module (601), a rotary module (602) and a clamping and placing module (603). The lifting module (601) is fixed on the second support frame (4), the rotary module (602) is fixedly arranged on one side of the lifting module (601), and the clamping and placing module (603) is fixedly arranged at the bottom of the rotary module (602).
5. The device for defect detection in the glass bottle production process according to claim 1, characterized in that: A light source module (9) is also arranged on one side of the conveying rack (1), and the light source module (9) is arranged opposite to the detection mechanism (5).
6. The device for defect detection in the glass bottle production process flow according to claim 1, characterized in that: A strip light source module (10) is also arranged on one side of the conveying rack (1), and the strip light source module (10) is arranged side by side with the detection mechanism (5) on the first support frame (3).
7. The device for defect detection in the glass bottle production process according to claim 3, characterized in that: The camera (501) is electrically connected to a controller, and the controller is electrically connected to the rotary lifting mechanism (6).
8. The device for defect detection in the glass bottle production process flow according to claim 6, characterized in that: The strip light source module (10) includes a strip light source, a strip light source rotating support plate and a strip light source fixing plate. The strip light source rotating support plate is fixedly arranged on the first support frame (3) through the strip light source fixing plate.