Material wrinkle detection method and device, electronic equipment and medium
By combining image processing and deep learning models, the accuracy problem of material wrinkle detection was solved, achieving efficient wrinkle detection and reducing production costs.
Patent Information
- Application Number
- CN202511716175.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-02-10
AI Technical Summary
Existing technologies cannot directly detect whether materials have wrinkles, and even when other dimensions are normal, there may still be missed detections, leading to increased production costs.
The basic dimensions and region images of the material are obtained through image processing, and then a pre-trained target deep learning model is used to detect whether wrinkles appear in the material.
It improves the accuracy and efficiency of material wrinkle detection, provides quality assurance for smart manufacturing, and reduces missed detections and production costs.
Smart Images
Figure CN121504895A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of tire manufacturing technology, and more specifically, to a method, apparatus, electronic device, and medium for detecting wrinkles in materials. Background Technology
[0002] In the tire forming process, the materials involved are soft and easily deformed. In particular, wrinkles are easily formed during the transportation of materials from material conveyors (such as conveyor belts) to tire forming machines (such as forming drums / belt drums). Wrinkles can lead to the production of scrapped green tires. Moreover, wrinkles are hidden, and manual inspection is time-consuming and easy to miss. They flow into subsequent processes and need to be reworked or scrapped, which will increase production costs.
[0003] In existing technologies, direct and effective alarms are not possible. Instead, other measurement dimensions, such as overlap, misalignment, material width, and off-center measurement, can be used to indirectly determine if wrinkles are present in the material. However, wrinkles may occur without corresponding anomalies in other dimensions; the detection process automatically continues once other dimensions pass inspection. After an alarm for a non-conformity is triggered, workers may only address the alarmed anomaly, ignoring less noticeable wrinkles, leading to missed detections. Therefore, existing technologies for detecting wrinkles in materials have the following drawbacks: 1. It cannot directly indicate whether there are wrinkles in the material.
[0004] 2. Wrinkles may also exist on materials with normal width and overlap values, which are easily missed by existing technologies.
[0005] Therefore, how to accurately detect whether materials have wrinkles has become an urgent problem to be solved. Summary of the Invention
[0006] This disclosure provides a method, apparatus, electronic device, and medium for detecting wrinkles in materials. By using image processing, the basic dimensions and material region images of the material are determined. The basic dimensions and material region images are then input into a pre-trained target deep learning model. The target deep learning model determines whether wrinkles have appeared in the material. This method improves the accuracy of wrinkle detection.
[0007] In a first aspect, embodiments of this disclosure provide a method for detecting wrinkles in materials, applied to a tire forming machine. The flexible material to be detected is bonded to the belt drum / forming drum of the tire forming machine. The method includes: Acquire the target stitched image corresponding to the flexible material to be tested. The target stitched image is stitched together from the various material transport images captured sequentially by an industrial camera during the material transport process of the flexible material to be tested on the material transport machine. Based on the target stitched image, the basic dimensions of the flexible material to be detected are determined. The basic dimensions include overlap, misalignment, off-center, and material width. Based on the basic dimensions, the location region of the flexible material to be detected in the target stitched image is determined, and the material region image containing the flexible material to be detected is extracted from the target stitched image based on the location region. The basic dimensions and material region images are input into a pre-trained target deep learning model, which determines whether the flexible material to be detected has wrinkles.
[0008] Secondly, embodiments of this disclosure provide a wrinkle detection device for materials, applied to a tire forming machine. The flexible material to be detected is bonded to the belt drum / forming drum of the tire forming machine. The device includes: The image acquisition module is used to acquire the target stitched image corresponding to the flexible material to be inspected. The target stitched image is stitched together from the various material transport images captured sequentially by an industrial camera during the material transport process of the flexible material to be inspected on the material transport machine. The first determining module is used to determine the basic dimensions of the flexible material to be detected based on the target stitched image. The basic dimensions include the overlap amount, misalignment amount, off-center amount, and material width. The second determining module is used to determine the location region of the flexible material to be detected in the target stitched image based on the basic dimensions, and to extract the material region image containing the flexible material to be detected from the target stitched image based on the location region. The third determination module is used to input the basic dimensions and material region image into the pre-trained target deep learning model, and to determine whether the flexible material to be detected has wrinkles through the target deep learning model.
[0009] Thirdly, embodiments of this disclosure provide an electronic device including a processor and a memory interconnected thereto; the memory is used to store a computer program; the processor is configured to execute, when the computer program is invoked, the method provided by any possible implementation of the wrinkle detection method for the material.
[0010] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the method provided in any possible implementation of the above-described method for detecting wrinkles in materials.
[0011] Fifthly, embodiments of this disclosure provide a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method provided in any possible implementation of the above-described method for detecting wrinkles in materials.
[0012] The beneficial effects of the technical solutions provided in this disclosure are: In this embodiment, during the bonding process of the flexible material to be tested on the belt drum / forming drum of the tire forming machine, it is necessary to detect in real time whether wrinkles appear in the flexible material to be tested. An industrial camera pre-installed is used to sequentially photograph the flexible material to be tested being transported on the material conveyor, obtaining individual material transport images. These images are then stitched together to obtain a corresponding target stitched image. Based on this target stitched image, the basic dimensions of the flexible material to be tested are determined through image processing. Based on these basic dimensions, the location region of the flexible material to be tested in the target stitched image can be determined. Based on this location region, a material region image containing the flexible material to be tested, with the background area removed, is extracted from the target stitched image. The determined basic dimensions and the material region image are then input into a pre-trained target deep learning model. The target deep learning model performs detection to determine whether wrinkles have appeared in the flexible material to be tested. Through the embodiments of this disclosure, on the one hand, the basic dimensions of the flexible material to be detected and the image of the material region containing the flexible material to be detected are determined in advance through image processing. This preprocessing method provides a basis for subsequent determination of whether wrinkles occur through a target deep learning model, thereby improving processing efficiency. On the other hand, wrinkle detection is performed by a trained target deep learning model, which combines information from both the basic dimensions and the material region image, thereby optimizing and upgrading the wrinkle detection process during tire forming. This provides reliable quality assurance for intelligent manufacturing and greatly improves the accuracy of material wrinkle detection. Attached Figure Description
[0013] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments of this disclosure will be briefly introduced below.
[0014] Figure 1 A schematic flowchart illustrating a method for detecting wrinkles in materials according to an embodiment of this disclosure; Figure 2 A schematic diagram of the material width of a flexible material to be tested, provided as an embodiment of this disclosure; Figure 3A schematic diagram of the structure of a material wrinkle detection device provided in an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation
[0015] The embodiments of this disclosure are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions of the embodiments of this disclosure.
[0016] To make the objectives, technical solutions, and advantages of this disclosure clearer, the embodiments of this disclosure will be described in further detail below with reference to the accompanying drawings.
[0017] The following description of several exemplary embodiments illustrates the technical solutions of this disclosure and the technical effects produced by these solutions. It should be noted that the following embodiments can be referenced, learned from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.
[0018] First, the technical terms used in this disclosure will be introduced and explained: I. Tire Forming Machine: A tire forming machine is a specialized piece of equipment used to assemble various semi-finished components (such as tread, ply, and bead rings) into a tire blank (green tire). It is one of the core pieces of equipment in the tire manufacturing process. Its technical complexity and precision directly affect the quality, uniformity, and performance of the tire.
[0019] II. Material Conveyor Systems: These refer to automated conveying systems used in tire manufacturing to automatically transport semi-finished tire products (such as rubber compounds, cord fabric, and bead sheets) and the formed green tires and vulcanized finished tires between different processes. The types of conveyors used vary depending on the shape and characteristics of the tires at different stages. The main types include: 1. Application in raw materials / semi-finished components (solid): These materials are usually in rolls or blocks, and are relatively strong. They are mainly transported by belt conveyors and roller conveyors.
[0020] 2. Used for green tires (critical and fragile stage): Green tires are tires that have been formed but not yet vulcanized. They are very soft and easily deformed, requiring special support conveying equipment. They are mainly transported through servo pallet conveying systems, autonomous mobile robots (AMRs), automated guided vehicles (AGVs), and V-belt green tire conveyors.
[0021] 3. Applied to finished tires after vulcanization. After vulcanization, the tires become harder and have a fixed shape, making the conveying methods more diverse and simpler. They are mainly transported by plate chain conveyors, roller conveyors, spiral slides, and tire lifts / lowers.
[0022] III. Area Scan Camera: The core feature of an area scan camera is that its sensor is a two-dimensional matrix (a "plane") composed of pixels. When the shutter is activated, all (or most) pixels on the sensor simultaneously or in a specific order receive light, thereby acquiring a complete two-dimensional image of the observed object in one go. The industrial camera involved in this disclosure is an area scan camera. Through this area scan camera, flexible materials to be inspected that are being transported on the surface of a material conveyor can be photographed to obtain various material transport images.
[0023] IV. Belt Drum: Also known as the belt layer bonding drum, it is the core component of the second stage forming machine in the two-stage tire building machine. It is a precision-engineered metal drum capable of high-speed rotation and complex radial expansion and contraction. Its main task is to combine the pre-cut steel belts and tread into a single unit with extremely high precision, and then transfer and fit it onto the first stage of the formed tire carcass.
[0024] 5. Forming Drum: This is the core component of the tire forming machine, which can be understood as a foldable and expandable "mold skeleton". Its function is to provide a precise fitting platform for all semi-finished tire components (such as carcass ply, belt layer, tread, etc.), and through its complex movement, wrap and shape the flat material into a cylindrical, uncured green tire.
[0025] The material wrinkle detection method in this embodiment can be executed by a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server or server cluster providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The aforementioned networks can include, but are not limited to, wired networks and wireless networks. Wired networks include local area networks (LANs), metropolitan area networks (MANs), and wide area networks (WANs). Wireless networks include Bluetooth, Wi-Fi, and other networks that enable wireless communication. Terminal devices can be smartphones (such as Android phones, iOS phones, etc.), tablets, laptops, digital broadcast receivers, MIDs (Mobile Internet Devices), PDAs (Personal Digital Assistants), desktop computers, in-vehicle terminals (such as in-vehicle navigation terminals), smart speakers, smartwatches, etc. Terminal devices and servers can be directly or indirectly connected via wired or wireless communication, but are not limited to these methods. Specific details can be determined based on actual application scenario requirements and are not limited here.
[0026] In tire manufacturing, the rubber composite materials used have significant flexibility, making them highly susceptible to deformation during transfer from the conveyor belt (material transport machine) to the forming drum / belt drum. This process often leads to the formation of wrinkles on the material surface, and these wrinkle defects directly result in the scrapping of green tires. Because wrinkles often exhibit subtle characteristics, manual visual inspection is not only inefficient but also carries a high risk of missing defects, allowing defective products to flow into subsequent production stages and ultimately necessitate rework or scrapping, significantly increasing manufacturing costs.
[0027] Current technical solutions have significant limitations. The system cannot directly and effectively detect and alarm for wrinkle defects; it can only indirectly infer potential wrinkle problems by monitoring other parameters such as joint overlap, material width, and center offset. However, in actual production, even if obvious wrinkles appear, these auxiliary parameters may still remain within acceptable ranges, and the system will consider it normal production and continue operating. Even when certain parameters abnormally trigger alarms, operators often only address the explicit problems indicated by the alarms, neglecting those less noticeable wrinkle defects, leading to serious missed detections. In summary, the existing technology mainly suffers from the following two key shortcomings: 1. It lacks a direct wrinkle detection function, making it impossible to accurately determine whether there are wrinkle defects on the surface of the material.
[0028] 2. Even when parameters such as material width and number of joints are normal, there may still be undetected wrinkles, and existing technical solutions are not effective in detecting such cases.
[0029] To address the aforementioned problems, this disclosure provides a method for detecting wrinkles in materials, applied to a tire forming machine. The flexible material to be tested is bonded to the belt drum / forming drum of the tire forming machine, such as... Figure 1 As shown, the method includes the following steps: Step S101: Obtain the target stitched image corresponding to the flexible material to be detected. The target stitched image is stitched together from the various material transport images captured sequentially by an industrial camera during the process of the flexible material to be detected being transported on the material transport machine. Step S102: Based on the target stitched image, determine the basic dimensions of the flexible material to be detected, including the overlap amount, misalignment amount, off-center amount, and material width. Step S103: Based on the basic dimensions, determine the location region of the flexible material to be detected in the target stitched image, and based on the location region, extract the material region image containing the flexible material to be detected from the target stitched image. Step S104: Input the basic dimensions and material region image into the pre-trained target deep learning model, and determine whether the flexible material to be detected has wrinkles through the target deep learning model.
[0030] Optionally, this disclosure can be applied to tire manufacturing scenarios. The flexible material to be tested can be understood as a material with a certain degree of flexibility and deformability, such as rubber materials, composite materials (composed of multiple flexible materials), elastomer materials, etc. For example, the flexible material to be tested includes a long strip of rubber with triangular ends used in tire production. Specifically, the flexible material to be tested may include a belt layer rubber sheet used in tire production. The belt layer rubber sheet is one of the components of the tire. It is a rubber coating on brass-plated steel cord, calendered or extruded onto the steel cord in the form of a thin sheet, cut at a certain angle and width, and then overlapped to form a continuous roll for tire molding. The belt layer formulation mainly targets fatigue resistance and tear resistance. It is understood that this disclosure does not limit the flexible material to be tested.
[0031] To detect whether wrinkles appear in the flexible material to be inspected during transport, a detection system provided in this disclosure embodiment can be used. This system comprises a material conveyor, a tire forming machine, an industrial camera, and a processing device. The material conveyor is used to transport the flexible material to be inspected, the tire forming machine is used to bond the flexible material to be inspected, and the processing device is used to perform image processing on a target stitched image formed by stitching together the various material transport images captured by the industrial camera. Based on the target stitched image, and combined with a target deep learning model, it detects whether wrinkles have appeared in the flexible material to be inspected.
[0032] First, it is necessary to acquire a target stitched image corresponding to the flexible material to be tested. In one optional embodiment, acquiring the target stitched image of the flexible material to be tested includes: receiving a start transmission signal forwarded by the tire forming machine controller, wherein, upon receiving the start transmission signal sent by the tire forming machine controller, the material conveyor controller controls the material conveyor to start transmitting the flexible material to be tested; sending a start transmission signal to an industrial camera, wherein, upon receiving the start transmission signal, the industrial camera acquires material transmission images at a preset image acquisition frequency within a preset material transmission time period; acquiring each material transmission image captured sequentially by the industrial camera; and stitching the various material transmission images together to obtain the target stitched image.
[0033] Optionally, the start and stop of the conveying of the flexible material to be tested are determined by signals sent by the tire forming machine controller. When the flexible material to be tested needs to be conveyed, the tire forming machine controller sends a start conveying signal to the material conveyor controller. Upon receiving the start conveying signal, the material conveyor controller controls the material conveyor to perform the material conveying operation. Both the tire forming machine controller and the material conveyor controller are programmable logic controllers (PLCs).
[0034] When the tire forming machine controller sends a start transmission signal to the material conveyor controller, it simultaneously sends the same start transmission signal to the processing equipment. Upon receiving the start transmission signal, the processing equipment forwards it to the industrial camera. Once the industrial camera receives the start transmission signal, it will capture images of the flexible material to be inspected within a preset material transmission time period, according to a preset image acquisition frequency, obtaining various material transmission images, and then transmit these images to the processing equipment.
[0035] The material transfer time period is the time required to transfer one piece of material, which is the time required to transfer the head and tail of the flexible material to be tested.
[0036] Then, the processing equipment receives the material transport images transmitted by the industrial camera and stitches them together sequentially according to the image acquisition time of each material transport image to obtain the target stitched image.
[0037] Image processing is performed on the target stitched image to determine its edges. These edges include the material edges. Based on the material edges and the definition of basic dimensions, the basic dimensions of the flexible material to be inspected can be determined. These basic dimensions include overlap, misalignment, off-center measurement, and material width. Overlap, also known as joint measurement, refers to the length of the overlapping portion when two rolls of material are joined together. Misalignment refers to the offset distance caused by the misalignment of the new and old materials in the width direction during joining. Off-center measurement refers to the offset distance between the centerline of the entire roll of material and the theoretical centerline of the production line or equipment during transmission. Material width refers to the actual width of the material.
[0038] Then, based on the determined basic dimensions, the location region of the flexible material to be detected in the target stitched image can be determined. Based on this location region, image cropping can be performed to extract the image containing only the region of the flexible material to be detected, thus obtaining the material region image and removing the interference region that does not contain the flexible material to be detected.
[0039] Finally, the material region image and basic dimensions are input into a pre-trained target deep learning model. This target deep learning model is specifically trained to detect whether the material image in the tire manufacturing process contains wrinkles, and has the function of accurately detecting whether wrinkles appear in the material region image.
[0040] The detection method uses a deep learning model to determine whether the flexible material to be detected has wrinkles.
[0041] Through the embodiments of this disclosure, on the one hand, the basic dimensions of the flexible material to be detected and the image of the material region containing the flexible material to be detected are determined in advance through image processing. This preprocessing method provides a basis for subsequent determination of whether wrinkles occur through the target deep learning model, thereby improving processing efficiency. On the other hand, wrinkle detection is performed by the trained target deep learning model, which combines information from both the basic dimensions and the material region image, greatly improving the accuracy of material wrinkle detection.
[0042] The following details how to determine the basic dimensions of the flexible material to be tested. In one optional embodiment, the basic dimensions of the flexible material to be tested are determined based on the target stitched image, including: performing image sharpening, image denoising, edge extraction, and morphological filtering operations on the target stitched image to obtain the image edges of the target stitched image; obtaining the material head position sent by the tire forming machine controller; determining the material head edge of the middle material head in the target stitched image based on the image edges and material head position of the target stitched image; determining the material tail edge of the material tail in the target stitched image based on the material head edge and standard material length information; determining the overlap and misalignment of the flexible material to be tested based on the material head edge and material tail edge; determining the left width vertex and right width vertex of the flexible material to be tested in the target stitched image based on the image edges of the target stitched image; determining the material width based on the left width vertex and right width vertex; and determining the off-center amount based on the image edges of the target stitched image and the centerline of the material conveyor.
[0043] Optionally, the material head and material tail mentioned in the embodiments of this disclosure will be introduced first. The flexible material to be tested is cut at a certain angle and width before lamination, including a material head and a material tail, wherein the material head can also be called the head and the material tail can also be called the tail. Taking the belt layer film as an example, the shape of the material head and the material tail is triangular.
[0044] The image edges of the target stitched image can be obtained by performing operations such as image sharpening, image denoising, edge extraction, and morphological filtering on the target stitched image. Then, the material head position sent by the tire forming machine controller is obtained. This material head position indicates the direction of the material head in the target stitched image, such as in the left area of the target stitched image. Based on the image edges of the target stitched image and the material head position, the material head edge in the target stitched image with respect to the material head can be determined.
[0045] Then, based on the position of the material head edge and the standard material length corresponding to the standard material length information, the material head edge is used as a reference, and the standard material length is used to determine the limited range. Within this limited range, the material tail edge corresponding to the material tail in the target splicing image can be determined.
[0046] Since both the head edge and tail edge of the material have corresponding coordinates, the distance between the head edge and tail edge can be determined based on these coordinates. This distance can be compared with the standard material length, and the overlap amount of the flexible material to be tested can be determined based on the definition of overlap amount.
[0047] Based on the image edges of the target stitched image, the upper and lower edges of the flexible material to be detected can be determined, as well as the distance between the upper and lower edges. Based on this distance, the misalignment amount of the flexible material to be detected can be determined.
[0048] The misalignment of the flexible material to be tested can be determined based on the coordinates of the material head edge and the material tail edge, and based on the definition of misalignment.
[0049] Figure 2 This is a schematic diagram of the material width of a flexible material to be tested provided in an embodiment of this disclosure. The following is in conjunction with... Figure 2 Please provide an explanation, such as Figure 2 As shown, Figure 2 The area between the two curves is the middle area connecting the head and tail of the material. It is shown in the figure by omitting the actual shape of the flexible material.
[0050] Based on the image edges of the target stitched image, the four vertices of the flexible material to be detected can be determined, such as... Figure 2 As shown, the four vertices are determined, including the head vertex 23 of the material head triangle, the vertex 21 where the material head triangle connects to the upper edge, the tail vertex 24 of the material tail triangle, and the vertex 22 where the material tail triangle connects to the lower edge. Vertex 23 is the left width vertex, and vertex 24 is the right width vertex. By drawing perpendicular lines from vertices 23 and 24, we can obtain perpendicular line 25 (which can be understood as the left width edge) and perpendicular line 26 (which can be understood as the right width edge). The distance between perpendicular lines 25 and 26 is the material width.
[0051] Based on the image edges of the target stitched image, the upper and lower edges of the flexible material to be detected can be determined, and the center line between the upper and lower edges can be determined. The distance between this center line and the center line of the material conveyor is the off-center amount.
[0052] Through the embodiments of this disclosure, the image edge of the flexible material to be detected can be determined by image processing. Based on the image edge and combined with other effective information, the basic dimensions of the flexible material to be detected can be determined, providing reference information for the subsequent target deep learning model, reducing the computational load of the target deep learning model, and thus improving the detection efficiency of the target deep learning model.
[0053] In an optional embodiment, after determining whether the flexible material to be detected has wrinkles through the target deep learning model, the method further includes: if wrinkles are determined to have occurred, sending a control signal to the tire forming machine controller, so that the tire forming machine controller controls the tire forming machine to perform stepping or stopping operations according to the control signal.
[0054] Optionally, if the target deep learning model determines that the flexible material to be tested does not have wrinkles, the material conveyor and the tire forming machine will both continue to operate under their original working models.
[0055] If the target deep learning model determines that the flexible material to be tested has wrinkles, a control signal needs to be sent to the tire forming machine controller. Upon receiving this control signal, the tire forming machine controller can, according to the signal's indication, control the tire forming machine to continue stepping or execute a stop operation, sending appropriate control signals as needed. At this time, the operator will receive a corresponding warning and inspect the equipment.
[0056] In addition, the industrial camera is mounted in front of the flexible material to be inspected and can extend and retract. When wrinkles appear, the industrial camera receives a stop shooting signal from the processing equipment. Upon receiving this stop shooting signal, the industrial camera stops shooting and retracts through the telescopic structure, giving the operator more workspace.
[0057] Through the embodiments disclosed herein, when wrinkles occur, the tire forming machine can be promptly controlled to advance or stop, thus avoiding greater losses and reducing costs.
[0058] In one optional embodiment, the target deep learning model is trained on the initial deep learning model by: acquiring a target image dataset, wherein each image in the target image dataset is labeled with a wrinkle category, and the target image dataset includes a training set; setting the input layer, convolutional layer, pooling layer, fully connected layer, activation function, loss function, and optimizer of the initial deep learning model to obtain a deep learning model with the set model architecture; training the deep learning model with the set model architecture based on the training set and the loss function, and adjusting the weights through the backpropagation algorithm until the loss function converges, and using the deep learning model with the set model architecture at the point of convergence as the target deep learning model.
[0059] Optionally, the target deep learning model is obtained by training the initial deep learning model. The specific training process is as follows: Step 1: Data collection and preprocessing.
[0060] In one optional embodiment, obtaining the target image dataset includes: collecting a set of tire crease images; labeling each image in the tire crease image set with a crease category; performing image resizing, pixel value normalization, rotation, scaling, and flipping operations on the tire crease image set to obtain the target image dataset; and dividing the target image dataset into a training set, a validation set, and a test set according to different functions.
[0061] Optionally, the training dataset should be as comprehensive as possible and consist of images of flexible materials in the tire manufacturing field. It should include images of various types of folds. The tire fold image set should be collected according to this standard and the images should be labeled to indicate the fold category of each image.
[0062] Preprocessing the images in the tire crease image set can increase the diversity of the data and reduce overfitting by adjusting the image size, normalizing the pixel values, rotating, scaling, and flipping. After these preprocessing operations, the target image dataset can be obtained.
[0063] Then, according to different functions, the target image dataset is divided into a training set, a validation set, and a test set. For example, the proportion of the training set can be 70%, the proportion of the validation set can be 15%, and the proportion of the test set can be 15%.
[0064] Step 2: Set the model architecture of the target deep learning model.
[0065] Optionally, the architecture of the deep learning model can be selected based on the requirements of accuracy, stability, and efficiency. Fine-tuning and reorganizing based on classic architectures, the selected model architecture is defined using a deep learning framework. Setting the input layer, convolutional layer, pooling layer, fully connected layer, activation function, loss function (such as cross-entropy loss), and optimizer of the initial deep learning model yields the deep learning model with the configured architecture. The activation function can be a Rectified Linear Unit (ReLU), and the optimizer can be either Stochastic Gradient Descent (SGD) or Adaptive Moment Estimation (Adam).
[0066] Step 3: Train the model using the training set.
[0067] Using the training set and loss function, a deep learning model with the configured model architecture is trained, and the weights are adjusted using the backpropagation algorithm to minimize the loss function. The loss value and accuracy are monitored during training, and hyperparameters such as learning rate and batch size are adjusted. When the loss function converges, the deep learning model with the converged model architecture is used as the trained target deep learning model.
[0068] Through the embodiments of this disclosure, training can be performed specifically on a set of tire crease images based on the field of tire manufacturing technology, which greatly improves the crease recognition rate.
[0069] In an optional embodiment, the target image dataset further includes a validation set and a test set. The method further includes: validating the target deep learning model through the validation set to obtain a validation evaluation index corresponding to the validation set; determining whether the target deep learning model is qualified based on the validation evaluation index; if it is unqualified, retraining; if it is qualified, testing the target deep learning model through the test set to obtain and record a test evaluation index corresponding to the test set; and determining the performance of the target deep learning model through the test evaluation index.
[0070] Optionally, the model's performance can be evaluated on a validation set to avoid overfitting. The model is evaluated using metrics such as accuracy and loss rate on the validation set. If the validation results are unsatisfactory, the model is retrained; if they are satisfactory, the final performance is evaluated on the test set to ensure good generalization ability. Metrics such as accuracy and confusion matrix on the test set are recorded to evaluate the model's performance.
[0071] Through the embodiments of this disclosure, the model can be evaluated using a validation set and a test set, thus ensuring the model's performance.
[0072] The following describes in detail the wrinkle detection method for materials in this disclosure, with reference to an embodiment. The method includes the following steps: The detection system of this embodiment mainly consists of a processing device, a camera, and a mechanical motion mechanism. The mechanical motion mechanism includes a tire forming machine and a material conveyor. The processing device connects the tire forming machine controller and the camera. The camera is installed in the mechanical motion mechanism in front of the object being tested. The camera is an industrial-grade camera that can scan multiple images of the object to be tested. These images are stitched together to obtain the target stitched image. The forming machine controller sends a start transmission signal and responds to operations such as acquisition and calculation. The corresponding result is calculated based on the target stitched image and fed back to the forming machine controller, thereby controlling the forming machine to perform stepping or stopping operations.
[0073] The detection system first detects basic dimensions such as joint amount, misalignment amount, off-center amount, and material width. The specific steps are as follows: 1. Determine the approximate area of the material head and extract the edge of the material head through operations such as image sharpening, image denoising, edge extraction, and shape filtering. Based on the material head position sent by the tire forming machine controller and combined with the standard material length information, comprehensively calculate the approximate area of the material tail, extract the edge of the material tail in this area, compare the position of the material head with the edge of the material position, and calculate the overlap amount.
[0074] 2. Based on the calculated joint position information, extract the approximate location of the misalignment, extract the misalignment edges through edge extraction and other operations, compare the upper and lower misalignment edges, and calculate the amount of misalignment.
[0075] 3. Determine the approximate location of the width edge, and extract the left and right width edges through image sharpening, image denoising, edge extraction, and shape filtering. By comparing the left and right width edges, the material width and off-center amount can be calculated.
[0076] After extracting basic dimensions such as joint amount, misalignment amount, off-center amount, and material width, the actual position of the material (i.e., the flexible material to be detected) in the target stitched image can be determined. Based on the actual position of the material in the target stitched image, a material region image containing only the material can be extracted from the target stitched image. Next, the wrinkle location is identified. The specific steps are as follows: 1. First, comprehensively judge whether there are any abnormalities in the current material head, material tail, misalignment and width edge. Input the joint amount, misalignment, width and off-center information into the deep learning model to determine whether there are any wrinkle abnormalities.
[0077] 2. After confirming that there are no anomalies in the edge information, input the image of the material area into the deep learning image classification model to determine whether any anomalies have occurred.
[0078] Combining the two judgment criteria, a comprehensive judgment is made on whether the material has wrinkles. The specific steps for using the deep learning model are as follows: 1. Data Collection and Preprocessing: Collect an image dataset containing multiple categories. The dataset should be as comprehensive as possible, including the diversity and variation of fold images across each category. Label the images, indicating the fold category to which each image belongs. Preprocess the images by adjusting image size, normalizing pixel values, rotating, scaling, flipping, etc., to increase data diversity and reduce overfitting. Divide the dataset into training, validation, and test sets in a ratio of 70% (training):15% (validation):15% (test).
[0079] 2. Select a deep learning model architecture based on the requirements of accuracy, stability, and efficiency. Fine-tune and reorganize based on classic architectures. Define the selected model architecture using a deep learning framework. Set the model's input layer, convolutional layer, pooling layer, fully connected layer, activation function (e.g., ReLU), loss function (e.g., cross-entropy loss), and optimizer (e.g., Adam, SGD).
[0080] 3. Train the model using the training set.
[0081] 4. Evaluate the model's performance on the validation set to avoid overfitting. Use metrics such as accuracy and loss on the validation set to evaluate the model. Evaluate the model's final performance on the test set to ensure good generalization ability. Record metrics such as accuracy and confusion matrix on the test set.
[0082] 5. In practical applications, continuously monitor the model's performance, collect new data, regularly update and retrain the model, and optimize and adjust the model based on feedback from different tire specifications and characteristics in different scenarios.
[0083] Well-trained deep learning models have the following advantages: 1. Detection accuracy: The accuracy rate of pleat recognition is ≥99.7%.
[0084] 2. Stability: Under continuous operation 24 / 7, the mean time between failures (MTBF) is >5000 hours.
[0085] 3. Adaptability: Supports automatic switching of 100+ tire specifications.
[0086] Through the embodiments disclosed herein, an innovative "traditional algorithm + deep learning" fusion architecture is used to optimize and upgrade the crease detection process during tire forming, providing reliable quality assurance for intelligent manufacturing.
[0087] This disclosure provides a wrinkle detection device for materials, applied to a tire forming machine. The flexible material to be detected is bonded to the belt drum / forming drum of the tire forming machine, such as... Figure 3 As shown, the device 30 may include: an image acquisition module 301, a first determination module 302, a second determination module 303, and a third determination module 304, wherein: The image acquisition module 301 is used to acquire the target stitched image corresponding to the flexible material to be detected. The target stitched image is stitched together from the various material transport images captured sequentially by an industrial camera during the process of the flexible material to be detected being transported on the material conveyor. The first determining module 302 is used to determine the basic dimensions of the flexible material to be detected based on the target stitched image. The basic dimensions include the overlap amount, misalignment amount, off-center amount, and material width. The second determining module 302 is used to determine the position region of the flexible material to be detected in the target stitched image based on the basic dimensions, and to extract the material region image containing the flexible material to be detected from the target stitched image based on the position region. The third determination module 303 is used to input the basic dimensions and material region image into the pre-trained target deep learning model, and determine whether the flexible material to be detected has wrinkles through the target deep learning model.
[0088] In an optional embodiment, the device further includes a control module configured to: if a wrinkle is determined to occur, send a control signal to a tire forming machine controller, so that the tire forming machine controller controls the tire forming machine to perform a stepping or stopping operation according to the control signal.
[0089] In an optional embodiment, the device further includes a model training module for: training an initial deep learning model to obtain a target deep learning model by: acquiring a target image dataset, wherein each image in the target image dataset is labeled with a wrinkle category, and the target image dataset includes a training set; setting the input layer, convolutional layer, pooling layer, fully connected layer, activation function, loss function, and optimizer of the initial deep learning model to obtain a deep learning model with the set model architecture; training the deep learning model with the set model architecture based on the training set and the loss function, and adjusting the weights through a backpropagation algorithm until the loss function converges, and using the deep learning model with the set model architecture at the point of convergence as the target deep learning model.
[0090] In one optional embodiment, the target image dataset further includes a validation set and a test set. The model training module is used to: validate the target deep learning model through the validation set to obtain the validation evaluation index corresponding to the validation set; determine whether the target deep learning model is qualified based on the validation evaluation index; if it is unqualified, retrain it; if it is qualified, test the target deep learning model through the test set to obtain the test evaluation index corresponding to the test set and record it; and determine the performance of the target deep learning model through the test evaluation index.
[0091] In one optional embodiment, the model training module is used to: collect a set of tire crease images; label each image in the tire crease image set with a crease category; perform image resizing, pixel value normalization, rotation, scaling, and flipping operations on the tire crease image set to obtain a target image dataset; and divide the target image dataset into a training set, a validation set, and a test set according to different functions.
[0092] In one optional embodiment, the first determining module 302 is specifically used for: performing image sharpening, image denoising, edge extraction, and morphological filtering operations on the target stitched image to obtain the image edges of the target stitched image; acquiring the material head position sent by the tire forming machine controller; determining the material head edge of the middle material head in the target stitched image based on the image edges and material head position of the target stitched image; determining the material tail edge of the material tail in the target stitched image based on the material head edge and standard material length information; determining the overlap and misalignment amount of the flexible material to be detected based on the material head edge and material tail edge; determining the left width vertex and right width vertex of the flexible material to be detected in the target stitched image based on the image edges of the target stitched image; determining the material width based on the left width vertex and right width vertex; and determining the off-center amount based on the image edges of the target stitched image and the centerline of the material conveyor.
[0093] In one optional embodiment, the image acquisition module 301 is specifically configured to: receive a start transmission signal forwarded by the tire forming machine controller, wherein, upon receiving the start transmission signal from the tire forming machine controller, the material conveyor controller controls the material conveyor to start transmitting the flexible material to be tested; send a start transmission signal to the industrial camera, wherein, upon receiving the start transmission signal from the industrial camera, the industrial camera acquires material transmission images at a preset image acquisition frequency within a preset material transmission time period; acquire each material transmission image captured sequentially by the industrial camera; and stitch the various material transmission images together to obtain a target stitched image.
[0094] Through the embodiments of this disclosure, on the one hand, the basic dimensions of the flexible material to be detected and the image of the material region containing the flexible material to be detected are determined in advance through image processing. This preprocessing method provides a basis for subsequent determination of whether wrinkles occur through the target deep learning model, thereby improving processing efficiency. On the other hand, wrinkle detection is performed by the trained target deep learning model, which combines information from both the basic dimensions and the material region image, greatly improving the accuracy of material wrinkle detection.
[0095] The apparatus of this disclosure embodiment can execute the method provided in this disclosure embodiment, and its implementation principle is similar, and it has corresponding technical effects. The actions performed by each module in the apparatus of each embodiment of this disclosure correspond to the steps in the method of each embodiment of this disclosure. For a detailed functional description of each module of the apparatus, please refer to the description in the corresponding method shown above, and it will not be repeated here.
[0096] This disclosure provides an electronic device (computer apparatus / device / system) including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method provided in any optional embodiment of this disclosure.
[0097] In one alternative embodiment, an electronic device is provided, such as Figure 4 As shown, Figure 4 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this disclosure.
[0098] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with this disclosure. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0099] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0100] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.
[0101] The memory 4003 is used to store computer programs that execute embodiments of the present disclosure, and is controlled by the processor 4001 to execute them. The processor 4001 is used to execute the computer programs stored in the memory 4003 to implement the steps shown in the foregoing method embodiments.
[0102] This disclosure provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.
[0103] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.
[0104] It should be understood that although arrows indicate various operation steps in the flowcharts of the embodiments of this disclosure, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of this disclosure, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured as required, and the embodiments of this disclosure do not limit this.
[0105] The above description is only an optional implementation method for some implementation scenarios of this disclosure. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this disclosure without departing from the technical concept of this disclosure also fall within the protection scope of the embodiments of this disclosure.
Claims
1. A method for detecting wrinkles in materials, applied to a tire forming machine, wherein the flexible material to be tested is bonded to the belt drum / forming drum of the tire forming machine, characterized in that... The method includes: Obtain a target stitched image corresponding to the flexible material to be tested, wherein the target stitched image is stitched together from various material transport images captured sequentially by an industrial camera during the material transport process of the flexible material to be tested on the material transport machine; Based on the target stitched image, the basic dimensions of the flexible material to be detected are determined, wherein the basic dimensions include overlap, misalignment, off-center, and material width. Based on the aforementioned basic dimensions, the location region of the flexible material to be detected in the target stitched image is determined, and based on the location region, a material region image containing the flexible material to be detected is extracted from the target stitched image. The basic dimensions and the image of the material region are input into a pre-trained target deep learning model, and the target deep learning model is used to determine whether the flexible material to be detected has wrinkles.
2. The method according to claim 1, characterized in that, After determining whether the flexible material to be detected has wrinkles using the target deep learning model, the method further includes: If wrinkles are detected, a control signal is sent to the tire forming machine controller, so that the tire forming machine controller can control the tire forming machine to perform stepping or stopping operations according to the control signal.
3. The method according to claim 1, characterized in that, The target deep learning model is obtained by training the initial deep learning model in the following way: Obtain a target image dataset, wherein each image in the target image dataset is labeled with a wrinkle category, and the target image dataset includes a training set; The input layer, convolutional layer, pooling layer, fully connected layer, activation function, loss function, and optimizer of the initial deep learning model are set to obtain the deep learning model with the set model architecture. Based on the training set and the loss function, a deep learning model with the configured model architecture is trained, and the weights are adjusted through the backpropagation algorithm until the loss function converges. The deep learning model with the configured model architecture at the point of convergence is then used as the target deep learning model.
4. The method according to claim 3, characterized in that, The target image dataset also includes a validation set and a test set, and the method further includes: The target deep learning model is validated using the validation set, and the validation evaluation index corresponding to the validation set is obtained. The validity of the target deep learning model is determined based on the verification and evaluation metrics. If the test is unsuccessful, the training must be repeated. If it passes, the target deep learning model is tested using the test set, and the test evaluation index corresponding to the test set is obtained and recorded. The performance of the target deep learning model is determined by the test evaluation metrics.
5. The method according to claim 3, characterized in that, The acquisition of the target image dataset includes: Collect a set of images of tire creases; Label each image in the tire crease image set with a crease category; The target image dataset is obtained by performing image resizing, pixel value normalization, rotation, scaling, and flipping operations on the tire crease image set. The target image dataset is divided into training set, validation set and test set according to different functions.
6. The method according to claim 1, characterized in that, The step of determining the basic dimensions of the flexible material to be detected based on the target stitched image includes: The target stitched image is subjected to image sharpening, image denoising, edge extraction, and morphological filtering operations to obtain the image edges of the target stitched image; Obtain the material head position sent by the tire forming machine controller; Based on the image edges of the target stitched image and the material head position, the material head edge of the material head in the target stitched image is determined; Based on the material head edge and standard material length information, the material tail edge in the target stitched image is determined; The overlap and misalignment of the flexible material to be tested are determined based on the edge of the material head and the edge of the material tail. Based on the image edges of the target stitched image, determine the left width vertex and the right width vertex of the flexible material to be detected in the target stitched image; The width of the material is determined based on the left width vertex and the right width vertex; The off-center amount is determined based on the image edges of the target stitched image and the centerline of the material conveyor.
7. The method according to claim 1, characterized in that, The process of acquiring the target stitched image corresponding to the flexible material to be detected includes: The material conveyor controller receives a start transmission signal forwarded by the tire forming machine controller, and upon receiving the start transmission signal sent by the tire forming machine controller, controls the material conveyor to start transmitting the flexible material to be tested. The start transmission signal is sent to the industrial camera, wherein, when the industrial camera receives the start transmission signal, the material transmission image is acquired at a preset image acquisition frequency within a preset material transmission time period. Acquire images of each material transfer sequentially captured by the industrial camera; The images of each material transport are stitched together to obtain the target stitched image.
8. A wrinkle detection device for materials, applied to a tire forming machine, wherein the flexible material to be detected is bonded to the belt drum / forming drum of the tire forming machine, characterized in that... The device includes: The image acquisition module is used to acquire a target stitched image corresponding to the flexible material to be detected. The target stitched image is stitched together from various material transport images captured sequentially by an industrial camera during the material transport process of the flexible material to be detected on the material transport machine. The first determining module is used to determine the basic dimensions of the flexible material to be detected based on the target stitched image, wherein the basic dimensions include overlap amount, misalignment amount, off-center amount and material width; The second determining module is used to determine the position region of the flexible material to be detected in the target stitched image based on the basic dimension, and to extract the material region image containing the flexible material to be detected from the target stitched image based on the position region. The third determining module is used to input the basic dimensions and the material region image into a pre-trained target deep learning model, and determine whether the flexible material to be detected has wrinkles through the target deep learning model.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-7.