Shearography system for detecting blowholes inside a tire

Abstract

The invention relates to a shearography system (100) incorporating a means for automatically segmenting anomalies detected by learning in tire images obtained by shearography. The invention also relates to a tire manufacturing plant comprising the disclosed shearography system. Figure for abstract: Fig. 5

Description

Title of the invention: Shearography system for detecting blowholes inside a tire Technical field

[0001] The invention relates to a shearography system for detecting blowholes inside a tire. More particularly, the invention relates to a system which performs the automatic diagnosis of anomalies of the "blowholes" or "bubbles" type detected by learning in the tire images obtained by shearography. Context

[0002] In the field of tire manufacturing, the interiors of tires intended to equip rolling vehicles are difficult to control. These tires generally have a black color due to the black rubber material that constitutes them (due to the use of carbon to reinforce the elastomeric compounds). In addition, blowholes (or "bubbles") inside tires are very difficult to produce. The existence of a blowhole may be linked to a known anomaly (which includes, without limitation, dents, scratches, cuts, chips, smooth teeth, missing or excess material and cracks). As used herein, the term "anomaly" refers to a detected difference (represented, for example, by a deviation from a standard value) without other information (therefore, an "anomaly" is not automatically interpreted as a "defect").

[0003] In the workshops for checking manufactured tires and retreaded tires, there are shearography machines with high control rates. Shearography refers to non-destructive testing (or "NDT") methods using interferometry in the visible wave domain (see Dubos, Camille et al., Shearographie: From the digital model to robotic inspection, JOURNEES COFREND 2023, https: / / doi.org / 10;58286:28523 (June 6-8, 2023) (the "Dubos reference"). Shearography is an optical technique for checking the porosity of composite materials (thus allowing the detection of blowholes inside a manufactured or retreaded tire). Shearography is recognized for its robustness with regard to environmental disturbances and vibrations (see the Dubos reference). Thus, there is a strong challenge in automating these machines.

[0004] However, one problem encountered by these machines concerns the production of extremely noisy images, with speckle noise inherent in their acquisition principle using interferometry. In industry, historical criteria that allow to distinguish an anomaly are the surface and the amplitude of the anomaly. The industry must therefore detect classes of different amplitudes, and it must also segment the anomalies to evaluate their surfaces. As an example, [Fig.l] represents a flank image (image (a) of [Fig.l]) and a vertex image (image (b) of [Fig.l]), being typical images obtained by a commercially available shear-ography machine.

[0005] Regardless of the type of tire, the steps of a verification method are substantially the same. The verification method includes a step of performing a preparation process, during which the operation of the sensors is checked, the sensors are calibrated, and the tire is placed in place for inspection. After the preparation process, the verification method includes a step of performing a data acquisition process, during which the sensors collect and record data corresponding to the position of the tire and its physical measurement. It is understood that the sensor(s) and / or the tire could be moved during this process. After the data acquisition process, the verification method includes a step of performing a data analysis process, during which the acquired data is analyzed and a report of the results is generated.The verification process includes a final step during which the results are saved and the tire is returned to the inspection chain of the verification workshop.

[0006] There are ongoing efforts to automate at least part of the tire inspection process. For example, one proposed solution uses a hybrid ensemble of convolutional neural networks (or "CNNs") with high-performance Faster Region-based CNNs. In this solution, region proposal generation and object detection are performed using CNNs to detect bubble anomalies in tire shearography images. Anomaly detection is performed using an artificial intelligence-based recognition algorithm for deep learning (i.e., "Faster R-CNN") that detects limiting anomalies. The proposed model primarily uses sliding-window CNNs to divide shearography images into regions to identify bubble anomalies.Subsequently, this step is followed by implementing the faster region-based CNNs method to identify bubble anomalies in tire shearography images. A faster region-based convolutional neural network (R-CNN) is chosen to minimize the false positive rate (see Chang, Chang, Chuan-Yu et al., Quality Assessment of Tire Shearography Images via Ensemble Faster Region-Based ConvNets, Electronics, doi.10.3390 / electronics9010045 (2020) (“the Chang reference”).

[0007] Other solutions propose the application of convolutional neural networks (or "fully convolutional networks" or "FCN") in the industrial field. For example, one solution proposes a method based on an FCN for precisely locating and segmenting anomalies in tire radiographic images (see Wang, Ren et al, "Tire Defect Detection Using Fully Convolutional Network", IEEE Access, doi:10.1109 / ACCESS.2019.2908483 (April 13, 2019) (the "Wang reference").

[0008] Another solution applicable to tire defect inspection proposes an end-to-end residual U-structure embedded U-Net with a hybrid loss function and a coordinated attention module (or "HLU2-Net") is proposed. In the HLU2-Net, a new residual U-structure is used to replace the encoding-decoding block of the U-Net to fuse the multi-scale and multi-level features. Furthermore, a coordinated attention module is introduced to highlight useful features and weaken irrelevant features (see Zheng, Zhouzhou, Zhang, Yan, and Yu, Bin, "HLU2-Net: A Residual U-Structure Embedded U-Net with Hybrid Loss for Tire Defect Inspection," IEEE Transactions on Instrumentation and Measurement, doi:10.1109 / TIM.2021.3126847 (February 2023)("the Zheng reference").

[0009] There are still major difficulties in detecting anomalies related to blow holes in tires. Poor visual quality makes it difficult to acquire tire images, and different machines used for automatic detection often have certain undesirable characteristics (such as low contrast and low brightness). In addition, tire images incorporate images of the tread and sidewalls, which consist of different textures (the tread is made of thick rubber, and the sidewall is largely made of rubber reinforced with fabric and / or steel cords). It is also understood that some anomalies exist only on the images of the tread and / or sidewalls.

[0010] In the tire manufacturing process, the diagnosis of "blow-out" type anomalies in tire images obtained by shearography represents an important task. Thus, the disclosed invention relates to the automatic verification of "blow-out" or "bubble" type anomalies detected by learning by building a model based on the labeled shearographic images. Summary of the invention

[0011] The invention relates to a shearography system incorporating a means for automatic segmentation of anomalies detected by learning in images of tires obtained by shearography, characterized in that the shearography system comprises: - a diagnostic apparatus incorporating a shearography device, the diagnostic apparatus comprising: - an inlet where tires intended for diagnosis are introduced into the device; - a processing space where the device's shearography device takes images of each tire positioned inside; and - an outlet where the tires leave the device for further processing; - a transfer means which transports to the device the tires intended for diagnosis by the device; - at least one scrolling conveyor which introduces the tires towards the entrance of the device to position them in the treatment space and to make them exit from the exit of the device; - a detection system that collects information on the physical environment around the shearography system, the detection system comprising one or more sensors that detect the presence of the tires in their field of vision; and - a communication network that manages the data entering the shearography system from the apparatus, the communication network comprising at least one communication server for executing programmed instructions stored in a memory of one or more processors of the shearography system that employs (a) an image processing module of the processor, which analyzes images obtained from the tires positioned in the processing space of the apparatus; and (b) a module for executing an anomaly detection algorithm from the data obtained from the shearographic images and video images of the tires; wherein the images taken are transferred and stored as captured images in the memory of the inspection system, and the memory, by executing the instructions of the image processing module, performs a diagnostic method comprising the following steps: - a step of detecting a tire positioned in the processing space of the device during which the device detects the presence of an arrangement of anomalies inside the tire in the detection field of the device; - an image capture step during which the device takes as input shearographic images and video images containing a visible label which allows the detection of an anomaly in the tire; and - a step of preprocessing the raw data of the images taken by the device, during which the pre-processed images are used as input to a trained neural network based on the Atrous Spatial Pyramid Pooling (ASPP) structure to obtain the results of segmentation of anomalies detected by learning in the taken tire images.

[0012] In certain embodiments of the shearography system of the invention, the ASPP structure is arranged between an encoder and a decoder.

[0013] In some embodiments of the shearography system of the invention, the trained neural network incorporates a stratified division performed on a data set obtained from the apparatus and a balancing of the training set; so that the stratified division allows to distribute training data, validation data and test data while maintaining a distribution of anomalies across all divisions.

[0014] In some embodiments of the shearography system of the invention, the shearography system is configured to determine: - a class probability of each tire image taken in a training sample; and - a defined loss function which is calculated by the error between each tire image and a corresponding label in the training sample.

[0015] In some embodiments of the shearography system of the invention, the defined loss function comprises a combination of IoULoss and CrossEntropy loss.

[0016] In some embodiments of the shearography system of the invention, the incoming data to the shearography system includes general information regarding an identified tire.

[0017] In certain embodiments of the shearography system of the invention, the sensor(s) of the detection system are arranged relative to the transfer means and the conveyor to manage the rate of introduction of the tires to the apparatus.

[0018] In some embodiments of the shearography system of the invention, at least one sensor of the detection system comprises one or more learning programming modes for feeding and training at least one neural network.

[0019] The invention also relates to a tire manufacturing installation comprising the disclosed shearography system.

[0020] Other aspects of the invention will become apparent from the following detailed description. Brief description of the drawings

[0021] The nature and various advantages of the invention will become more apparent upon reading the following detailed description, in conjunction with the accompanying drawings, in which the same reference numbers designate identical parts throughout, and in which: [Fig.l] [Fig.l] represents a flank image and a vertex image obtained by a known shearography machine. [Fig.2] [Fig.2] represents a schematic cross-sectional view of an embodiment of a known tire. [Fig.3] [Fig.3] represents an embodiment of a diagnostic system of the invention which implements a method allowing the automatic diagnosis of anomalies inside one or more tires. [Fig.4] [Fig.4] depicts exemplary shearographic and video images taken of a tire during a diagnostic process implemented by the system of [Fig.3]. [Fig.5] [Fig.5] represents the architecture of a model of a neural network trained by the system of [Fig.3]. [Fig.6] [Fig.6] represents a representation of the improvement in pixel detection accuracy obtained by the presence of ASPP in the model of [Fig.5]. [Fig.7] [Fig.7] represents an embodiment of training the neural network represented in [Fig.5]. Detailed description

[0022] When considering the characteristics of a tire intended for a diagnostic process, its geometry must be taken into account. A tire is an object having a known geometry generally comprising several superimposed layers of rubber (or "layers"), as well as a metal or textile fiber structure constituting a reinforcing carcass of the tire structure. The nature of the rubber and the nature of the reinforcement are chosen according to the desired final characteristics. [Fig. 2] comprises a schematic representation of a tire 10 comprising, in a conventional manner, two circumferential beads intended to allow the tire to be attached to a rim. Each bead comprises an annular reinforcing bead. The constitution of a tire is typically described by a representation of its constituents in a meridian plane, that is to say a plane containing the axis of rotation of the tire.The radial, axial and circumferential directions respectively designate the directions perpendicular to the axis of rotation of the tire, parallel to the axis of rotation of the tire, and perpendicular to any meridian plane. The expressions "radially", "axially" and "circumferentially" mean respectively "in a radial direction", "in the axial direction" and "in a circumferential direction" of the tire. The expressions "radially inner" and "radially outer" respectively mean "closer, respec . tively further away”, from the axis of rotation of the tire, in a radial direction.

[0023] The tire 10 also comprises a tread 12, including a tread surface 12a and an inner surface 12b. The tread 12 is intended to come into contact with a ground via a tread surface 12a. The inner surface 12b ensures that pressure is maintained in the tire.

[0024] The tire 10 further comprises a crown reinforcement comprising a working reinforcement 14 and a hoop reinforcement 16, the working reinforcement 14 having working layers represented by layers 14a and 14b. The tire 10 also comprises two sidewalls (a sidewall 18 being represented in [Fig.l]) and two fillers 20 reinforced with a bead wire 22. A radial carcass layer 24 extends from one bead to the other, surrounding the bead wire in a known manner. The tread 12 comprises reinforcements consisting, for example, of superimposed layers comprising known reinforcing threads. In embodiments, the tire may include a rubber 26 which evacuates the static electricity produced during rolling.

[0025] The tread 12 is delimited, in the radial direction, by two circumferential surfaces, the most radially outer of which is the tread surface 12a and the most radially inner of which is called the tread base surface. The tread base surface (or "bottom surface") is defined as the surface translated from the tread surface radially inward by a radial distance equal to the tread depth. It is common for this depth to decrease on the most axially outer circumferential portions (called "shoulders") of the tread 12.

[0026] In addition, the tread of a tire is delimited, in the axial direction, by two lateral surfaces. The tread is further constituted by one or more rubber compounds.

[0027] In order to obtain wet grip performance, cutouts are arranged in the tread 12. A cutout designates either a well, a groove, an incision, or a circumferential furrow and forms a space opening onto the tread surface 12a. The performance of a tread pattern must be sufficiently constant despite the wear of said strip to ensure the durability of the tire. Consequently, it is necessary to maintain a certain thickness of rubber materials between the bottom face of the cutouts (grooves or furrows) and the reinforcing elements to guarantee the endurance of the tire. For example, grooves must have sufficient widths to allow evacuation of the liquid present on the surface of the ground regardless of the stage of wear of the tread (12).

[0028] Referring to the figures, in which the same numbers identify identical elements, [Fig. 3] represents an embodiment of a shearography system (or "system") 100 of the invention. The system 100 implements a diagnostic method (or "method") allowing the automatic diagnosis of anomalies of the "blowing" or "bubbles" type inside one or more tires P (it is understood that the term "anomaly" is used here to refer to the blowing, bubbles and corresponding anomalies). The method incorporates a machine learning method which is based on the data corresponding to the tire images obtained by shearography. It is understood that the system 100 can be part of a tire manufacturing facility.

[0029] As used herein, the term “method” or “process” may include one or more steps performed by at least one computer system having one or more processors to execute instructions that perform the steps. Unless otherwise indicated, any sequence of steps is given by way of example and does not limit the described methods to any particular sequence. It is understood that the system 100 can implement the diagnostic method in any physical environment without prior knowledge of the pattern of anomalies to be detected on the inner surfaces of the imaged tires. By performing the method, the system 100 achieves continuous improvement in recognizing anomalies and their relative positioning along the inner surface of a tire.

[0030] The system 100 comprises a diagnostic apparatus (or "apparatus") 102 which comprises a shearography device as known to those skilled in the art. The tires intended for diagnosis by the apparatus 102 arrive by a known transfer means (for example, one or more tires P could arrive at the system 100 by means of one or more conveyors 104 as shown in [Fig. 3]). The tires P arrive one at a time on a conveyor 106 which ensures the scrolling of each tire towards an inlet 102a of the apparatus 102 (see arrow A of [Fig. 3]).

[0031] After its introduction to the apparatus 102, the introduced tire is positioned in a processing space where the apparatus 102 will image it (see [Fig. 3] where the tire P* represents such a positioned tire). During this step, the tire P* is placed in position in the apparatus 102 so that the shearography device of the apparatus 102 can take images of the tire. It is understood that the identified tire could be positioned by the conveyor 106 on a work table or on an equivalent support so that the apparatus 102 can image it. The support can be configured to move in a rotational manner, in an alternating vertical manner and / or in an alternating horizontal manner, thus allowing the taking of images of a variety of tires.

[0032] When the apparatus 102 detects the tire P* positioned in the apparatus 102, the apparatus 102 detects the presence of an arrangement of anomalies inside the tire P* in the detection field of the apparatus, which triggers it to capture the image of a surface of the tire P*. The apparatus 102 (and particularly its shearography device) takes images of the tire P* detected in the apparatus 102, including the taking of one or more videos of the tire P*. This substantially simultaneous taking of images and videos allows the attribution of labels to the anomalies, which facilitates their subsequent detection. The system 100 “searches”, in the images obtained, for the presence of the anomalies “seen” by the shearography device. If no anomalies are detected, the shearography device continues to obtain the images until the search for the tire is exhausted.

[0033] At the end of a diagnostic process carried out by the apparatus 102, the conveyor 106 transports each imaged tire P to an output 102b of the apparatus for further processing (for example, storage of the checked tires, subsequent analysis for the tires that require it, and / or removal of the tires bearing one or more anomalies).

[0034] The system 100 also includes a detection system (not shown) for collecting information about the physical environment around the system. The detection system includes one or more sensors (including one or more cameras) configured to perform two-dimensional (2D) and / or three-dimensional (3D) image detection, 3D depth detection, and / or other types of detection of the physical environment around the system 100 (it is understood that the terms "sensor" and "camera" are used interchangeably). In embodiments of the system 100 shown in [Fig. 3], the sensor(s) of the detection system could be attached above, beside, and / or around the system 100 (and particularly arranged relative to the conveyors 104 and 106 to manage the transfer rate and the scrolling of the tires P, respectively).In embodiments of the system of the invention, these sensors could be part of an overall detection system that employs these sensors together with one or more sensors positioned in the physical environment in which the system 100 is installed. It is understood that one or more sensors (including cameras) may include one or more programming modes, including by learning, to feed, modify and train at least one neural network.

[0035] To properly manage the scrolling of the tires P towards the device 102, which ensures the clear capture of images of each identified tire, it is necessary to identify the tire being diagnosed and detect the positioning of the anomalies concerned. Thus, the detection data refers to a plurality of recordings representative of the positions of the anomalies of at least one known tire or a portion of a known tire tracked over time. For example, the sensing data may include one or more of recordings of the positions of a reference point on a portion of the tire (e.g., the inner surface 12b) over time or at defined time intervals; sensor data taken over time; a video stream that has been processed using a computer vision technique; and / or data indicative of the operating status of the apparatus 102 over time. In some cases, the sensing data may include data representative of one or more continuous movements of the conveyor 106 before it stops so that the apparatus 102 can take one or more images of a tire.

[0036] Referring again to [Fig. 3], to implement the computer-based diagnostic method, the system 100 comprises a communication network (or "network") 108 which manages the data incoming to the system 100 from various sources (for example, from the apparatus 102 and its associated shearography device). The communication network 108 incorporates one or more communication servers (or "servers") 108a each comprising one or more processors operatively connected to a memory. The memory is configured to store an application for analyzing data representative of the imaged tires (and more particularly, the images taken of the interior surfaces of these imaged tires).The processor(s) includes an analysis application execution module that performs image processing, wherein the processor(s) is / are capable of executing programmed instructions stored in memory to perform the steps of the diagnostic method (as described below).

[0037] The incoming data to the system 100 may include general information regarding an identified tire. The general information includes stored data regarding the identification of the identified tire (including, without limitation, its production origin, distribution and / or storage, production date, retread history if applicable, and mounting position and history). The general information may also include the retread rank (if applicable) of the identified tire. Data corresponding to a retread rank of an identified tire is typically managed by the entity that manages the use of one or more identified tires (e.g., a person(s) and / or a company(ies)) and / or the manufacturer of such tires.

[0038] The term "processor" (or, alternatively, the term "programmable logic circuit") means one or more devices capable of processing and analyzing data and comprising one or more software programs for their processing (for example, one or more integrated circuits known to those skilled in the art as being included in a computer, one or more controllers, one or more microcontrollers, one or more several microcomputers, one or more programmable logic controllers (or "PLCs"), one or more application-specific integrated circuits, one or more neural networks, and / or one or more other known equivalent programmable circuits). The processor includes one or more software programs for processing the data captured by the apparatus 102 and the detection system of the system 100 as well as one or more software programs for identifying and locating variances and identifying their sources to correct them.

[0039] In the system 100, the memory may include both volatile and non-volatile memory devices. The non-volatile memory may include solid-state memories, such as NAND flash memory, keep-alive memory (KAM) for saving various operating variables while the processor is powered off, magnetic and optical storage media, or any other suitable data storage device that retains data when the system 100 (or a portion of the system 100) is powered off or loses power. The volatile memory may include static and dynamic RAM that stores program instructions and data, including a learning application.

[0040] In embodiments of the system 100, the processor can configure the apparatus 102 (and in particular its shearography device) on one or more parameters calculated by an image processing module incorporated in the memory of the processor. The image processing module analyzes the images of the tires and, more precisely, the images of the anomalies seen by the shearography device of the apparatus 102.

[0041] The processor may also refer to a reference (e.g., a size chart of various tires) to make a final determination of one or more parameters of a tire being imaged. The reference may include parameters of a plurality of known commercially available tires. For example, after the image processing module calculates one or more parameters of the imaged tire (see, for example, tire P* being imaged by apparatus 102 in [Fig. 3]), the processor may compare the calculated parameters with the known parameters stored in the reference. The processor may retrieve the known tire parameters corresponding to the commercially available tires that most closely match the parameters calculated to configure apparatus 102.The tire reference may include measurements corresponding to a plurality of commercially available tires. For example, for a tire of size 225 / 50R17, the number "225" identifies the tire's cross-sectional area in millimeters, the number "50" indicates the sidewall aspect ratio, and the measurement "R17" represents the diameter of the . rim in inches (being approximately 43.18 centimeters).

[0042] It is understood that one or more sensors (including cameras) may include one or more programming modes, including by learning, to feed, modify and train at least one neural network. Referring again to [Fig. 3], and further to [Fig. 4], the neural network which takes as input the stereographic images obtained by the apparatus will also take charge of a video image obtained by the detection system of the system 100. The system takes as input the two types of images in order to take into account the presence of labels, which will be more visible on the video image. For example, [Fig. 4] represents a shearographic image (image (a) of [Fig. 4]) and a video image (image (b) of [Fig. 4]). The video image contains a visible label which makes it possible to detect an anomaly, thus providing information so as not to detect the “traces” around the detected anomaly.

[0043] Referring again to Figures 3 and 4, and further to Figures 5 and 6, [Fig. 5] represents an architecture of the model trained by the system 100. The architecture of the model represented in [Fig. 5] is based on a neural network incorporating the Atrous Spatial Pyramid Pooling (or "ASPP") structure together with an encoder 200 and a decoder 202. To classify a pixel, the ASPP exploits multi-scale characteristics by employing several parallel filters with different rates. The advantage is that it allows us to take into account a context that is more spatially distant from the pixel to be classified (for example, instead of taking 9 contiguous pixels in the “feature map”, we will look for pixels a little further away) (see Chen, Liang-Chieh et al., DeepLah: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs, https: / / doi.org / 10.48550 / arXiv.1606.00915 (May 12, 2017)(“the Chen reference”). [Fig.6] represents the results of this ASPP structure which improves the accuracy on pixel detection, particularly the comparison of the loss rate of the training set and the validation set (image (a) of [Fig.4]) and the overlap rate of the training set and the validation set (image (b) of [Fig.4]).

[0044] Thus, the system 100 provides a means for automatically segmenting anomalies of the “blows” or “bubbles” type detected by learning in the tire images obtained by shearography. During a diagnostic method implemented by the system 100, raw image data collected by the apparatus 102 (the shearographic images) are obtained and preprocessed by the network 108. The preprocessing is performed to form training samples which are divided into three parts: training set, validation set and test set to verify the performance of the trained network. The preprocessed images are taken as input to the model architecture based on the ASPP structure to obtain anomaly segmentation results. Based on this, the system 100 determines the class probability of each tire image in the training sample; the defined loss function calculates the error between each tire image and the corresponding label in the training sample. Based on the error and an offset from the predefined conditions, the model parameters are updated.

[0045] The ASPP structure is defined in the network to capture the multi-scale information of anomalies. Therefore, the original data can be directly extracted efficiently to obtain fast and accurate segmentation results: a supervised method based on deep learning mainly trains the model and label images through a neural network, automatically extracts relevant features of anomalies, and automatically completes the segmentation.

[0046] Referring to Figures 3 to 6, and further to [Fig.7], [Fig.7] shows an embodiment of training the neural network shown in [Fig.5]. To improve the results, a stratified split is performed on a data set obtained from the device 102 and a balancing of the training set. This consists of (1) homogeneously distributing the shearographic images obtained from the device 102 between “training”, “validation” and “test”; and (2) repeating the rare indices in the training set in order to present the different classes in an equivalent manner. The stratified split makes it possible to distribute the training data, the validation data and the test data while maintaining the distribution of anomalies in all the splits (i.e., there is the same proportion in the training / validation / test split). During the training process of the model shown in [Fig.5], a balanced split-train means that for training, and only for training, we artificially balance by recalling the “rare” examples at regular intervals. It is possible to experiment with several strategies to have more levers with additional hyperparameters that allow us to better define the balance between wrong / wrong detection.

[0047] The loss function is a combination of IoULoss which penalizes bad intersections over unions and CrossEntropy loss. The different parameters are chosen precisely from PRCurves (with the threshold on the abscissa and the precisions for the classes in question on the ordinate); the kernel size in order to eliminate singular points which can lead to the detection wrongly; and the trigger threshold (in mm2) for each anomaly class allowing the final classification of the pneumatic.

[0048] Compared with the prior art, the disclosed system 100 has the following beneficial effects: - the disclosed system 100 uses an architecture based on the ASPP structure to directly extract the features of the original data information, and directly segment the target based on the obtained features, which has high efficiency and does not depend on manual intervention; - the constructed model has an ASPP structure that can capture the multi-scale information of the "blowing" or "bubbling" type anomalies and can effectively extract the multi-scale receptive field of the high-level feature map feature, which improves the model's ability to effectively reduce the loss of anomaly feature information during the transmission processes.

[0049] Thus, the advantage of segmentation is that one could detect both the surface characteristic of the tire but also classify the different types of amplitudes into different classes.

[0050] A diagnostic process may be performed by the PLC control and may include pre-programming of management information. For example, a process setting may be associated with the parameters of the tire being imaged, and / or the properties of tires already imaged in a tire manufacturing facility incorporating the system 100. The system 100 (and / or a facility incorporating the system 100) may readily repeat one or more steps of the process in a determined order to ensure training of the disclosed model.

[0051] The system 100 (and / or a tire manufacturing facility incorporating the system 100) may include preprogramming of management information. For example, a process setting may be associated with the parameters of the typical physical environments in which the system 100 operates. In embodiments of the invention, the system 100 (and / or a tire manufacturing facility incorporating the system 100) may receive voice commands or other audio data representing, for example, a step or a stop in taking images (either shearographic images or video images). A request may be made that includes a request for the current status of a running diagnostic process cycle. A generated response may be represented audibly, visually, tactilely (e.g., using a haptic interface), and / or in a virtual and / or augmented manner.This response, combined with the corresponding data, can be stored in a neural network.

[0052] For all embodiments of the system 100, a monitoring system could be implemented. At least a portion of the monitoring system may be provided in a portable device such as a mobile network device (e.g., a telephone mobile, a laptop, one or more network-connected wearable devices (including “augmented reality” and / or “virtual reality” devices), network-connected wearable clothing and / or any combinations and / or equivalents). It is conceivable that detection and comparison steps can be carried out iteratively.

[0053] The terms "at least one" and "one or more" are used interchangeably. Ranges that are presented as being "between a and b" encompass the values ​​"a" and "b".

[0054] Although particular embodiments of the disclosed apparatus have been illustrated and described, it will be understood that various changes, additions, and modifications may be practiced without departing from the spirit and scope of the present disclosure. Accordingly, no limitations should be imposed on the scope of the disclosed invention except those set forth in the appended claims.

Claims

Claims

1. A shearography system (100) incorporating means for automatically segmenting anomalies detected by learning in tire images obtained by shearography, characterized in that the shearography system (100) comprises: - a diagnostic apparatus (102) incorporating a shearography device, the diagnostic apparatus (102) comprising: - an inlet (102a) where tires (P) intended for diagnosis are introduced into the device; - a processing space where the shearography device of the apparatus (102) takes images of each tire (P) positioned therein; and - an outlet (102b) where the tires (P) exit the apparatus (102) to carry out further processing; - a transfer means (104) which transports to the device (102) the tires (P) intended for diagnosis by the device; - at least one moving conveyor (106) which introduces the tires (P) towards the inlet (102a) of the device (102) to position them in the treatment space and to make them exit from the outlet (102b) of the device; - a detection system which collects information on the physical environment around the shearography system (102), the detection system comprising one or more sensors which detect the presence of the tires in their field of vision; and - a communication network (108) which manages the incoming data to the shearography system (100) from the apparatus (102), the communication network comprising at least one communication server (108a) for executing programmed instructions stored in a memory of one or more processors of the shearography system which employs (a) an image processing module of the processor, which analyzes images obtained from the tires (P) positioned in the processing space of the apparatus (102); and (b) a module for executing an anomaly detection algorithm from the data obtained from the shearographic images and the video images of the tires (P); wherein the images taken are transferred and stored as captured images in the memory of the inspection system (100), and the memory, by executing the instructions of the image processing module, executes a diagnostic method comprising the following steps: - a step of detecting a tire (P*) positioned in the processing space of the apparatus (102) during which the apparatus (102) detects the presence of an arrangement of anomalies inside the tire (P*) in the detection field of the apparatus; - an image taking step during which the apparatus (102) takes as input shearographic images and video images containing a visible label which makes it possible to detect an anomaly of the tire (P*);and - a step of preprocessing the raw data of the images taken by the apparatus (102), during which the preprocessed images are used as input to a trained neural network based on the Atrous Spatial Pyramid Pooling (ASPP) structure to obtain the results of the segmentation of anomalies detected by learning in the tire images taken.;

2. The shearography system (100) of claim 1, wherein the ASPP structure is arranged between an encoder (200) and a decoder (202).

3. The shearography system (100) of claim 2, wherein the trained neural network incorporates a stratified division performed on a set of data obtained from the apparatus (102) and a balancing of the training set; such that the stratified division allows training data, validation data and test data to be distributed while maintaining a distribution of anomalies across the divisions.

4. The shearography system (100) of claim 3, wherein the shearography system (100) is configured to determine: - a class probability of each tire image taken in a training sample; and - a defined loss function which is calculated by the error between each tire image (P) and a corresponding label in the training sample.

5. The shearography system (100) of claim 4, wherein the defined loss function comprises a combination of IoULoss and CrossEntropy loss.

6. The shearography system (100) of any one of the claims- indications 1 to 5, wherein the incoming data to the shear-rography system includes general information concerning an identified tire.

7. The shearography system (100) of any one of claims 1 to 6, wherein the sensor(s) of the detection system are arranged relative to the transfer means (104) and the conveyor (106) to manage the rate of introduction of the tires (P) to the apparatus (102).

8. The shearography system (100) of any one of claims 1 to 7, wherein at least one sensor of the detection system comprises one or more learning programming modes for feeding and training at least one neural network.

9. A tire manufacturing plant comprising the shearography system of any one of claims 1 to 8.

Images