A tire defect appearance detection system
By designing a tire defect appearance inspection system, and utilizing a visual inspection module and deep learning algorithms, the problems of inconsistent inspection results and high difficulty in identification during tire production have been solved. This system achieves automated and accurate defect identification, improving inspection efficiency and product quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- SICHUAN YUANXING RUBBER CO LTD
- Filing Date
- 2025-04-10
- Publication Date
- 2026-07-07
AI Technical Summary
In the current tire production process, the detection of appearance defects relies on human experience, which leads to inconsistent detection results and makes it difficult to form objective evaluation standards. In addition, the wide variety of defect types increases the difficulty of identification and reduces detection efficiency and accuracy.
A tire defect appearance detection system was designed, including a power roller line module, a feeding and flexible clamping and positioning module, a clamping module, a vision inspection module, a tire displacement module, and an electronic control signal system. The system automatically identifies tire surface defects using the vision inspection module and deep learning algorithms.
It enables automated and accurate tire defect identification, improves detection efficiency and accuracy, reduces human error, lowers the defect rate, and enhances product quality and economic benefits.
Smart Images
Figure CN224471584U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of tire inspection technology, and in particular to a tire defect appearance inspection system. Background Technology
[0002] Accurate detection of tire appearance defects is crucial in the tire manufacturing process. However, current inspection procedures suffer from numerous operational pain points, severely impacting efficiency and accuracy. On one hand, traditional inspection methods heavily rely on the experience and eyesight of inspectors, making results susceptible to subjective influences and difficult to guarantee consistency. On the other hand, tire appearance defects are diverse, including cracks, bubbles, impurities, scratches, and uneven tread patterns, increasing the difficulty of identification and further reducing inspection efficiency. Furthermore, differing understandings of inspection standards among employees and the lack of a unified training system lead to highly subjective results, making it difficult to establish objective and quantifiable evaluation standards. Utility Model Content
[0003] The purpose of this invention is to design a tire defect appearance detection system to solve the above problems.
[0004] This utility model achieves the above objectives through the following technical solutions:
[0005] This utility model provides a tire defect appearance inspection system, including a power roller line module, a feeding and flexible clamping and positioning module, a clamping module, a vision inspection module, a tire displacement module, and an electronic control signal system architecture.
[0006] As a preferred embodiment of this invention, the powered roller conveyor module comprises an infeed powered roller conveyor, a bullseye transmission mechanism, and an outfeed powered roller conveyor. The tire is initially conveyed via the infeed powered roller conveyor to the bullseye transmission mechanism (visual inspection area). After visual inspection, the tire lifting and shifting module moves the tire to the outfeed powered roller conveyor, which then transmits it to the downstream production line.
[0007] As a preferred embodiment of this invention, the feeding and flexible clamping positioning module includes a feeding detection fiber optic cable, a lifting electric cylinder, and a flexible clamping positioning mechanism. When the tire is transmitted to the position of the bullseye transmission mechanism via the feeding power roller line in the previous step, the feeding detection fiber optic cable detects the tire's position. Once the tire is detected to be in position, a signal is transmitted to the lifting electric cylinder, which rises to the correct position. Then, the flexible clamping positioning mechanism begins to operate, aligning the center position of the tire.
[0008] As a preferred embodiment of this invention, the clamping module includes a clamping centering servo module and a servo rotation module. After the tire is aligned, the clamping centering servo module clamps and positions the tire, and the servo rotation module rotates the tire after clamping.
[0009] As a preferred embodiment of this invention, the visual inspection module includes an upper visual inspection displacement module, a side visual inspection displacement detection module, and a lower visual inspection displacement module. After the tire rotates into position, the visual inspection module, through data exchange with the distance sensor, moves to the corresponding detection position and performs surface inspection on the tire.
[0010] The entire system is controlled by an electronic control signal system, which comprises four parts: a tire position detection system, a motion control system (sending signals to the aforementioned modules), a vision control computer, and vision software. These four parts work together to ultimately complete tire defect detection. Specifically, the photoelectric sensor in the tire position detection system detects whether the tire is in the detection position, and the distance sensor measures the working distance from the tire detection surface to the vision inspection module. After receiving the tire positioning signal, the vision control computer (host computer) works with the clamping module and the vision inspection module to perform image detection on the tire. The vision inspection software outputs the measurement results, which are then sent to the computer. The human-machine interface on the computer automatically / manually switches between programs, triggers alarms for abnormal states, and the vision software displays the tire defect detection results.
[0011] The beneficial effects of this invention are as follows: it can automatically extract complex features and identify minute defects on the tire surface (such as cracks, bubbles, foreign objects, etc.) with high accuracy and generalization ability. It can significantly improve detection efficiency, reduce labor costs, improve product quality, and generate significant economic benefits. Simultaneously, through high-precision defect detection, the system can effectively reduce the defect rate and improve product quality. It has good operational feasibility; the system equipment is simple and easy to use, fully utilizing the advantages of modern computer technology and overcoming many errors caused by manual inspection. The system can automatically complete the entire process from image acquisition and processing to defect identification without complex operations. This greatly reduces operational difficulty and minimizes the occurrence of human error. Attached Figure Description
[0012] Figure 1 This is a schematic diagram of the structure of the present invention. Figure 1 .
[0013] Figure 2 This is a schematic diagram of the structure of the present invention. Figure 2 .
[0014] Figure 3 This is a schematic diagram of the structure of the present invention. Figure 3 .
[0015] In the diagram: 1-Feeding power roller conveyor, 2-Bullseye transmission mechanism, 3-Discharge power roller conveyor, 4-Feeding detection fiber optic cable, 5-Lifting electric cylinder, 6-Clamping module, 7-Side vision inspection module, 8-Upper vision inspection module, 9-Lower vision inspection module, 10-Tire lifting and shifting module. Detailed Implementation
[0016] To make the objectives, technical solutions, and advantages of the embodiments of this utility model clearer, the technical solutions of the embodiments of this utility model will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this utility model. The components of the embodiments of this utility model described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0017] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0018] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0019] In the description of this utility model, it should be understood that the terms "upper", "lower", "inner", "outer", "left", "right", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the utility model product is usually placed in during use, or the orientation or positional relationship that is commonly understood by those skilled in the art. They are only used to facilitate the description of this utility model and to simplify the description, and are not intended to indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this utility model.
[0020] Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.
[0021] In the description of this utility model, it should also be noted that, unless otherwise explicitly specified and limited, terms such as "set" and "connection" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this utility model according to the specific circumstances.
[0022] The specific embodiments of this utility model will now be described in detail with reference to the accompanying drawings.
[0023] As attached Figure 1-3 As shown, this embodiment provides a tire defect appearance inspection system, including a power roller line module, a feeding and flexible clamping positioning module, a clamping module, a vision inspection module, a tire displacement module, and an electronic control signal system architecture.
[0024] As a preferred embodiment of this utility model, the power roller conveyor module comprises a feeding power roller conveyor 1, a bullseye transmission mechanism 2, and a discharging power roller conveyor 3. The tire is conveyed from the feeding power roller conveyor 1 to the bullseye transmission mechanism 2 (visual inspection area), where the tire lifting and shifting module 10 moves the tire to the discharging power roller conveyor 3, from which it is transferred to the downstream production line.
[0025] In a preferred embodiment of this utility model, the feeding and flexible clamping positioning module includes a feeding detection fiber optic cable 4, a lifting cylinder 5, and a flexible clamping positioning mechanism. When the tire is transmitted to the position of the bullseye transmission mechanism 2 via the feeding power roller line 1 in the previous step, the feeding detection fiber optic cable 4 detects the tire position. When the tire is detected to be in position, a signal is transmitted to the lifting cylinder 5, which rises to the correct position. Then, the flexible clamping positioning mechanism starts to operate, aligning the center position of the tire.
[0026] In a preferred embodiment of this utility model, the clamping module 6 includes a clamping centering servo module and a servo rotation module. After the tire is aligned, the clamping centering servo module clamps and positions the tire, and the servo rotation module rotates the tire after clamping.
[0027] In a preferred embodiment of this utility model, the visual inspection module includes an upper visual inspection displacement module 8, a side visual inspection displacement detection module 7, and a lower visual inspection displacement module 9. After the tire rotates into position, the visual inspection module moves to the corresponding detection position through data exchange with the distance sensor to perform surface inspection on the tire.
[0028] In a preferred embodiment of this utility model, the entire system is controlled by an electronic control signal system, which includes four parts: a tire position detection system, a motion control system (sending signals to the aforementioned modules), a vision industrial control computer, and vision software. These four parts cooperate with each other to ultimately complete tire defect detection. Specifically, the photoelectric sensor in the tire position detection system detects whether the tire is in the detection position, and the distance sensor measures the working distance from the tire detection surface to the vision detection module. After receiving the tire positioning signal, the vision industrial control computer (host computer) uses the clamping module 6 in conjunction with the vision detection module to perform image detection on the tire. The vision detection software generates the measurement results, which are then sent to the computer. The computer's human-machine interface automatically / manually switches between programs, triggers alarms for abnormal states, and the vision software displays the tire defect detection results.
[0029] Working principle: The tire inspection system can acquire image data of the tire surface in real time during the tire production process. Using advanced algorithms, it analyzes and processes the images to reconstruct the tire's defect model, accurately identifying various potential defects such as cracks, cuts, and foreign object embedding. The identified defects are classified, and automatic warnings are issued to remind production personnel to address them promptly.
[0030] The most important defect detection is based on deep learning algorithms for processing and analysis, and its working principle can be divided into two main steps. The first step is to generate a deep learning model of tire surface defects and deploy the model, and the second step is real-time defect detection.
[0031] Step 1: Generate and deploy the defect model
[0032] (1) Image acquisition and preprocessing
[0033] High-resolution tire surface images are acquired through a visual inspection module, including images of normal tires and tires with surface defects. The acquired images are then preprocessed, such as cropping and image enhancement, to improve image quality.
[0034] (2) Constructing the dataset and defect annotation
[0035] The images collected in the previous step are used to construct a labeled dataset containing various tire defects. The location and type of defects in the images (such as cracks, cuts, foreign object embedding, etc.) are quickly marked using the intelligent annotation method in AI software.
[0036] The labeled dataset is divided into training, validation, and test sets for training and tuning deep learning models.
[0037] (3) Deep learning training and validation
[0038] The model type is selected based on the type and distribution of image defects in the dataset and the overall size of the dataset. Then, the model is trained using a labeled training set. During training, the model continuously adjusts its parameters through backpropagation to reduce the error between the prediction results and the actual labeled information. Finally, the model's performance is evaluated using a validation set. If the model results are not good, the training parameters (such as the number of training images, the number of batches, etc.) are readjusted to improve the model's generalization ability.
[0039] (4) Model Deployment
[0040] The trained defect model is deployed to the host computer software to realize automated detection and data interaction of the defect detection system.
[0041] Step 2: Real-time detection
[0042] (1) Real-time defect detection
[0043] On the production line, tire images collected in real time are input into a trained defect model. The model extracts and compares features from the input images and uses corresponding algorithms to determine whether there are defects in the current image and the location and type of the defects.
[0044] (2) Alarm
[0045] If a defect is found in the current tire, the system will automatically trigger an alarm. The results of the tire defect detection will also be displayed on the vision software.
[0046] Working process: The tire begins to be conveyed when it passes through the feeding power roller line 1, and the feeding detection fiber optic 4 monitors the position of the tire on the power roller line in real time.
[0047] When the tire is detected to have reached the bullseye transmission mechanism 2, the feed detection fiber optic cable 4 will send a signal back to the electronic control system.
[0048] The electronic control system then controls the lifting cylinder 5 to rise to the predetermined position, ensuring that the tire is accurately lifted to the detection height. The flexible clamping and positioning mechanism then begins to operate, and through adaptive adjustment, ensures that the center position of tires of different types and sizes remains consistent, so as to ensure the accuracy of subsequent detection.
[0049] Subsequently, the clamping and rotating module 6 is activated, causing the tire to rotate. Once the tire has rotated to the preset position, the upper vision inspection module 7, lower vision inspection module 8, and side vision inspection module 9 automatically adjust to the corresponding inspection positions based on data exchange with the distance sensor, performing a comprehensive inspection of the tire surface to detect defects such as cracks, cuts, and embedded foreign objects, ensuring that the tire surface is free of defects and damage. If a defect is detected on the tire surface, an abnormal alarm is triggered.
[0050] After the tire surface inspection is completed, the tire transfer module 10 starts to move, removing the tire from the bullseye transmission mechanism 2 and moving it to the discharge power roller line 3. The discharge power roller line 3 continues to convey the tire to the downstream production line for subsequent processing or packaging.
[0051] This tire appearance inspection system technology achieves automated, high-precision tire inspection and transfer, ensuring production efficiency and product quality stability.
[0052] Although the present invention has been described herein with reference to illustrative embodiments, the above embodiments are merely preferred embodiments of the present invention, and the implementation of the present invention is not limited to the above embodiments. It should be understood that those skilled in the art can design many other modifications and implementations, which will fall within the scope and spirit of the principles disclosed in this application.
Claims
1. A tire defect appearance inspection system, characterized in that, include: The power roller conveyor module, feeding and flexible clamping positioning module, clamping module (6), vision inspection module, tire lifting and shifting module (10), and electrical control signal system; The power roller line module includes: a feeding power roller line (1), a bullseye transmission mechanism (2), and a discharging power roller line (3). The tire is conveyed through the feeding power roller line (1) to the bullseye transmission mechanism (2) for visual inspection. The feeding and flexible clamping positioning module includes: a feeding detection optical fiber (4), a lifting electric cylinder (5), and a flexible clamping positioning mechanism; The tire passes through the visual detection area and the tire position is detected by the feed detection fiber (4); The feed detection fiber (4) can transmit signals to the lifting cylinder (5) through the electronic control signal system, so that the lifting cylinder (5) rises to the position; and the center position of the tire is aligned by the flexible clamping and positioning mechanism. The visual inspection module includes: an upper visual inspection displacement module (8), a side visual inspection displacement module (7), and a lower visual inspection displacement module (9). After the tire rotates to the correct position, the visual inspection module moves to the corresponding inspection position through data exchange with the distance sensor and performs surface inspection on the tire. The tire lifting and shifting module (10) can move the tire to the discharge power roller line (3), and then transmit it to the back-end production line through the discharge power roller line (3).
2. The tire defect appearance inspection system according to claim 1, characterized in that: The clamping module (6) includes a clamping centering servo module and a servo rotation module. After the tire position is aligned, the clamping centering servo module clamps and positions the tire. After the tire is clamped, the servo rotation module rotates to drive the tire to rotate.
3. The tire defect appearance inspection system according to claim 1, characterized in that: The system is controlled by an electronic control signal system, which includes: a tire position detection system, a motion control system, a vision industrial computer, and vision software. The photoelectric sensor of the tire position detection system is used to detect whether the tire has reached the detection position; the distance sensor of the tire position detection system is used to measure the working distance from the tire detection surface to the visual detection module. The vision control computer is used to receive the tire positioning signal and perform imaging detection on the tire through the clamping module (6) in conjunction with the vision detection module, thereby obtaining the measurement result; The vision-based industrial control computer can send the results to the computer terminal, and can automatically / manually switch between programs through the human-machine interface on the computer terminal, and can alarm for abnormal states.