Method for automatically repairing damage to a tire

Abstract

The invention relates to a method for automatically repairing damage to a ply comprising metal cables of a tire carcass, the method comprising the following steps: - detecting (step R1) the position of at least one anomaly zone and of a healthy zone in an image of at least one cord of the ply; - categorizing (step R2) the detected anomaly zone according to two types of anomaly zone, an anomaly zone intended to be brushed if rubber is present in direct proximity to the anomaly zone, and an anomaly zone intended to be ground for any other anomaly zone; - selecting (step R3) the repair tool from either a brush or a grinding wheel depending on the category of anomaly zone detected; and - repairing (step R7) the cord using the selected repair tool on the cord.

Description

[0001] DESCRIPTION

[0002] TITLE: Automatic Repair Method for Damage to a Tire

[0003] technical field

[0004] The present invention relates to the detection of damage and its repair on a tire, for example a tire suitable for equipping a vehicle such as a motor vehicle, a heavy goods vehicle or an airplane.

[0005] In particular, the present invention relates to the automatic detection and repair of damage located at the level of a layer comprising metal cables of a tire carcass.

[0006] The present invention can more generally be implemented for the purpose of retreading a tire.

[0007] Previous techniques

[0008] A tire, and in particular the plies or carcass of a tire, is generally repaired entirely by hand when such a repair step is possible.

[0009] The purpose of this step is to repair the various damages sustained by the tire carcass during rolling. At the beginning of this step, the tire is carded; in other words, the remaining worn tread is removed using a carding machine, in order to make accessible the tire's plies, which are then considered to be exposed or, more precisely, coated with a thin layer of rubber.

[0010] A tire carcass is defined as a tire whose tread has been removed, leaving a layer of metal cords exposed.

[0011] A tire web is a metallic web that includes a set of metal cables, coated with a thin layer of rubber, allowing the tire to be encircled and its resistance guaranteed.

[0012] A tire tread, for example, is susceptible to corrosion and rust, which attacks the various cables. One solution to remove this rust is to use a grinding wheel directly on the cables.

[0013] Another possible damage is the presence of so-called "unhealthy" cables with structural anomalies, such as cut cables, cables that bend, or cables or cracked insulation, etc.

[0014] In order to know which areas of the tire carcass to repair, some current solutions use colorimetric analysis to identify the presence of rust.

[0015] However, no existing method exists to identify damage other than the presence of rust.

[0016] Furthermore, no existing method exists to automate the search for these other damages, the detection of damages, and their repair.

[0017] Description of the invention

[0018] The present invention therefore aims to overcome the aforementioned drawbacks and to provide an automatic and efficient method for repairing a tire casing.

[0019] The present invention relates to a method for the automatic repair of damage to a layer comprising metallic cables of a tire casing, the method comprising the following steps:

[0020] - Detection of the position of at least one anomaly zone and one healthy zone on an image of at least one cable of the ribbon cable;

[0021] - Categorization of the detected anomaly zone according to two types of anomaly zone, an anomaly zone intended to be brushed if gum is present in the vicinity of said anomaly zone, and an anomaly zone intended to be ground for any other anomaly zone;

[0022] - Choice of repair tool between a brush and a grinding wheel depending on the category of the detected anomaly area; and

[0023] - Repair of the cable using the chosen repair tool on the cable itself. This process automates the detection and repair of a tire casing. Furthermore, it optimizes the repair by taking into account the nature of the damaged area to select the appropriate repair tool.

[0024] In a particular implementation method, the anomaly zone categorization step categorizes said anomaly zone as an anomaly zone intended to be brushed if gum is present within 5 cm, preferably within 2 cm, or even more preferably in contact with said anomaly zone.

[0025] In one implementation mode, the detection step is followed by a grouping step of several detected anomaly zones into a primary anomaly zone when said anomaly zones are located at a distance less than a predefined distance from each other.

[0026] Advantageously, the process includes, before the repair step, a step of enlarging an anomaly zone to a predefined minimum size when said anomaly zone has a size less than said predefined minimum size.

[0027] In a particular mode of implementation, the repair step is implemented so that the repair tool has a translational movement along the longitudinal direction of the cable from the healthy area to the anomaly area, as well as a rotational movement about an axis orthogonal to the translational movement and in the opposite direction to a rolling direction of the repair tool on said cable.

[0028] Advantageously, the process takes into account the orientation of the cables, which allows for better maintenance and / or cutting, especially since damage, particularly corrosion damage, generally propagates along a cable and not transversely.

[0029] Implementing a rotational movement perpendicular to the translational movement and opposite to the direction of rotation of the repair tool on the cable also allows for better maintenance and / or cutting of the tire carcass ply cables. Advantageously, the brush includes rigid metal bristles adapted for removing rubber from the tire carcass ply cables, the grinding wheel being made of carbide or stone.

[0030] Advantageously, the detection step includes the detection of the position of at least one anomaly zone, preferably including a structural anomaly, by machine learning and optionally by image processing in visible, multispectral or infrared color, the image of at least one cable of the ribbon being a visible, multispectral or infrared color image.

[0031] In a particular embodiment, the method includes a prior step of acquiring an image, preferably a secondary image in visible colors, multispectral or infrared, of at least one cable of the ribbon cable.

[0032] Advantageously, the method includes, after the detection step, a registration step of a primary image of the tire acquired by a main imaging system fixed relative to the tire carcass with the image, preferably the secondary image in visible colors, multispectral or infrared, acquired by a secondary imaging system mobile relative to the tire carcass and whose field of observation is included in the field of observation of the main imaging system, the registration step being implemented by applying a registration homography to said main image or to said secondary image.

[0033] The present invention also relates to an industrial repair system comprising a fixed main imaging system including one or two cameras adapted to acquire a three-dimensional point cloud, a mobile secondary imaging system, preferably with a visible, multispectral or infrared color sensor, whose field of observation is included in the field of observation of the main imaging system, an effector including a repair tool, the repair system including means for implementing the process as defined above, the effector being controlled by the main imaging system to perform the repair step.

[0034] The present invention also relates to a computer program comprising instructions which, when the program is executed by a computer, lead the computer to implement the steps of the process as defined above.

[0035] The system includes, for example, a computer and a computer-readable data medium, with the computer program as defined above being stored on the data medium.

[0036] Brief description of the drawings

[0037] Other objects, features and advantages of the invention will become apparent from the following description, given solely by way of non-limiting example, and made with reference to the accompanying drawings in which:

[0038] [Fig 1] is a schematic representation of the different stages of the process of repairing a tire casing according to the invention;

[0039] [Fig 2] is a schematic representation of an industrial repair system according to the invention;

[0040] [Fig 3] is a schematic representation of anomaly zones detected during the process according to figure 1;

[0041] [Fig 4] is a schematic representation of the anomaly zone grouping step implemented in the process according to figure 1;

[0042] [Fig 5] is a schematic representation of the step of repairing an anomaly zone implemented in the process according to figure 1;

[0043] [Fig 6] is a schematic representation of the step of repairing a defect area implemented in the process according to Figure 1, in the opposite direction to that shown in Figure 5. Detailed description of at least one embodiment

[0044] Figure 1 schematically represents the different stages of an automatic repair process for damage to a tire casing according to the invention.

[0045] The process is implemented for example by means of an industrial repair system 1 represented in figure 2, for example a computer 3.

[0046] The industrial repair system 1 also includes a fixed primary imaging system 5 and a mobile secondary imaging system 7. These two imaging systems 5 and 7 are adapted to image an object to be observed 9, in this case a tire 9, or more precisely, a tire casing 9. This is, in fact, a tire from which the tread has been removed. The surface of the tire casing 9 has a layer of metal cords coated with a thin layer of rubber material, the rubber.

[0047] The industrial repair system 1 includes a robot 1 comprising one or more arms, one of the arms being able to support the main imaging system 5 and / or the secondary imaging system 7.

[0048] The industrial repair system 1 includes an effector 13, in other words a tooling element, supported by a robot arm 11, enabling the repair of the tire casing 9 to be carried out.

[0049] The effector 13 includes at least one repair tool, for example a brush, also called a hard brush, and / or a grinding wheel.

[0050] The brush includes stiff metal bristles suitable for removing residual gum from a wired panel of a tire carcass.

[0051] The grinding wheel, for example, comprises a hard material such as carbide or stone and is adapted for cutting sections of wire cables, particularly sections of cables that have been sheared and are curling back. After the grinding wheel passes over a sheet of wire, the cables are straight and pressed against the carcass of the tire 9, their ends having been cut at an angle to follow the curvature of said tire carcass 9.

[0052] The main imaging system 5 is said to be fixed because it is adapted to image the tire carcass 9 from a fixed point at a fixed working distance Dp from said tire carcass 9, for example between 500 and 700 mm, preferably 600 mm.

[0053] The primary imaging system 5 can be a 3D imaging system comprising, for example, one or two cameras, such as RGB-D cameras, adapted to acquire a three-dimensional point cloud. Subsequently, the primary image, or any other image acquired by the primary imaging system 5, is projected onto a plane perpendicular to the shooting direction to obtain a color image; the three-dimensional point cloud is used solely for robot control.

[0054] The secondary imaging system 7 is said to be mobile because it is adapted to image the tire carcass 9 from different locations, however preferably with a fixed working distance Ds, for example between 150 and 350 mm, preferably 300 mm.

[0055] The secondary imaging system 7 can be a 2D imaging system with a visible color sensor, multispectral or infrared, preferably multispectral. Indeed, for the visual inspection of tire carcasses 9, infrared, particularly near-infrared, makes it possible to highlight defects in the wiring of the cables.

[0056] The presence of rust, for example, is easily detected at wavelengths in the near-infrared range.

[0057] The secondary imaging system 7 includes, for example, a 25 mm focal length lens for a sensor with dimensions between 10 and 15 mm wide and between 5 and 7 mm high.

[0058] The primary imaging system 5 and the secondary imaging system 7 have a common image acquisition and / or display method; in other words, their data can be compared to detect similar features represented in the two images acquired by the two different systems. Preferably, the common method is image acquisition in the same type of color register, for example RGB, YCbCr, CMYK, or grayscale.

[0059] The YCbCr and CMYK color registers are also registers preferred by the secondary imaging system 7, as rust appears better in the image in these color registers.

[0060] Advantageously, the field of view of the secondary imaging system 7 is smaller, for example, covering an area at least 10 times smaller, and therefore falls within the field of view of the primary imaging system 5. For example, the dimensions of the field of view of the secondary imaging system 7 are between 65 and 85 mm in width and between 35 and 70 mm in height. Preferably, the resolution of the secondary imaging system 3 is higher than the resolution of the primary imaging system 5.

[0061] Thus, the main imaging system 5 provides an overview of the tire carcass 9, for example to guide and control the effector 13 in space for the repair of said tire carcass 9. The secondary imaging system 7 provides specific information on certain areas, for example damaged areas, of the tire carcass 9.

[0062] The implementation of the automatic repair process for damage to a layer comprising metal cables of a tire carcass is particularly suitable for a worn tire that will be retreaded.

[0063] Prior to implementing this process, a step is performed to remove the tread, that is, the rubber on the outer periphery of the tire, in order to subsequently apply a new tread made of one or more strips of rubber material. A curing step is then carried out to vulcanize this rubber material. Removing the worn tread yields a tire carcass. The outer surface of the carcass consists of a layer of metal wire coated with rubber material. Optionally, a brushing step is also performed beforehand to expose the cords of the layer.

[0064] The steps of this process are illustrated in Figure 1.

[0065] We first perform an RI step to detect the position of at least one anomaly zone and a healthy zone on an image of at least one cable of the ribbon cable.

[0066] The image on which the areas of anomaly and healthy areas are detected is, for example, a secondary image acquired by the secondary imaging system 7 as described above, preferably multispectral.

[0067] In a particular embodiment, the present method includes the prior implementation of an RO step for acquiring said image, preferably the secondary image, in visible color, multispectral or infrared, of at least one cable of the ribbon cable.

[0068] In one particular implementation, the IR detection step includes the detection of the position of at least one anomaly zone using machine learning. This type of detection makes it possible to detect structural anomalies, which was not possible in the prior art.

[0069] Machine learning, for example, uses a neural network and an unsupervised learning method which, starting from a first image containing an anomaly in the tire casing, can reconstruct a second image of the undamaged tire casing. By comparing the first and second images, it is easy to highlight an area of ​​anomaly.

[0070] Optionally, the RI detection step is also performed using visible, multispectral, or infrared color image processing, with the image of at least one cable in the ribbon cable being a visible, multispectral, or infrared color image. This processing allows, in particular, the detection of rust, grease (i.e., heated rubber with a greasy and / or melted appearance), or blue discoloration of the cables. Then, an optional R2 step is performed to categorize the detected anomaly zones according to at least two types of anomaly zone, for example, as shown in Figure 3: an anomaly zone intended for brushing (Z1) and an anomaly zone intended for grinding (Z2), with a clean zone designated Z0.

[0071] In particular, an anomaly zone intended for brushing is categorized as such if G-stain is present in the vicinity of said anomaly zone; any other anomaly zone is categorized as an anomaly zone intended for grinding. "In the vicinity" means positioning the G-stain in the immediate vicinity of the anomaly zone, in other words, within 5 cm, preferably less than 2 cm, or even more preferably in contact with the anomaly zone.

[0072] Anomaly zones are preferably represented as a rectangle whose length follows the longitudinal direction of the C cables.

[0073] Then, we carry out step R3 of choosing a repair tool between a brush and a grinding wheel, the repair step being implemented with the chosen repair tool.

[0074] Preferably, a repair of the anomaly area intended to be brushed (ZI) is carried out with the brush. As this area is at the edge of the rubber (G), it is necessary to brush the rubber to remove it and to check that the detected anomaly has not spread under the rubber along the cables, as is regularly the case with rust, for example.

[0075] Once an anomaly zone intended to be brushed ZI has actually been brushed during the repair step R7 described below, it can be recategorized as an anomaly zone intended to be ground Z2 if it actually corresponds to this category.

[0076] Preferably, a repair of the anomaly area intended for grinding (Z2) will be carried out using the grinding wheel. This allows the cable to be cut or removed to prevent it from bending back or simply to permanently remove the rust.

[0077] Then, optionally, a step R4 is performed to group several detected anomaly zones, where appropriate anomaly zones of the same type, into a primary anomaly zone when said anomaly zones are located at a distance less than a predefined distance from each other.

[0078] This step R4 is represented in Figure 4 where different anomaly zones intended to be brushed ZI are grouped into a larger anomaly zone intended to be brushed ZI.

[0079] Following the same principle, an optional R5 step is performed to enlarge an anomaly area to a predefined minimum size when the anomaly area is smaller than this predefined minimum size. The predefined minimum size depends on the dimensions of the repair tool(s) being considered. Specifically, the predefined minimum size must be greater than the tool's cut width and footprint length. For example, the width of an anomaly area is between 1 and 4 cm; this dimension must be converted to pixels in the image acquired by the secondary imaging system. The length of the anomaly area is, for example, twice its width.

[0080] This allows the repair tool to more easily move over the different areas of detected anomaly and thus make the repair more efficient, without redundancy.

[0081] Optionally, and advantageously before the R7 repair step, a R6 registration step is performed of a primary image of the tire acquired by the main imaging system 5 fixed relative to the tire carcass with the image, preferably the secondary image in visible colors, multispectral or infrared, acquired by the secondary imaging system 7 mobile relative to the tire carcass and whose field of observation is included in the field of observation of the main imaging system.

[0082] The R6 registration step is implemented by applying a registration homography to said main image or to said secondary image.

[0083] This R6 registration step allows for a perfect superposition of the primary and secondary images respectively acquired by the main imaging system 5 and the secondary imaging system 7, and thus to be able to precisely control the effector 13 in space thanks to the wide view of the main imaging system 5 and the precision of the information of the secondary imaging system 7.

[0084] Finally, step R7 is performed to repair the cable using the repair tool on said cable. This step R7 is illustrated schematically in Figure 5.

[0085] Advantageously, the repair tool 15 is placed in contact with the tire casing 9 tangentially to the surface of said tire casing 9. The repair tool 15 then undergoes a translational movement M1 along the longitudinal direction of the cable C from the sound zone ZO to the anomaly zone Z1 or Z2. This movement M1 optimizes the repair by taking into account the cable orientation, which allows for better maintenance and / or cutting, especially since damage generally propagates along a cable and not transversely.

[0086] Combined with the translational movement, the repair tool 15 has a rotational movement M2 about an axis orthogonal to the translational movement M1 and in the opposite direction to the rolling direction M3 of the repair tool on the cable. The direction of this movement is important and helps prevent the cables from bending back.

[0087] Having reached the center of the anomaly zone ZI or Z2, the repair tool 15 stops and is placed at another end of the anomaly zone ZI or Z2 as schematically illustrated in Figure 6. The repair step R7 is then implemented again in the reverse direction in order to repair the anomaly zone ZI or Z2 at each of its longitudinal ends.

[0088] The R7 repair step is notably carried out with the grinding wheel and can therefore be a grinding step.

[0089] Step R7 finally allows the automated repair of a ribbon cable of a damaged tire carcass.

[0090] Step R7 also allows for grinding the cables and removing the rubber above an underlying layer of the tire casing to expose the cables of said underlying layer and allow for analysis of their condition. If an anomaly is detected on the underlying layer, it is then possible to repeat the various steps of this repair procedure.

[0091] In general, the implementation of the steps of this process, in particular step R7 of repair with a brush or a grinding wheel, is repeated as many times as necessary on an area of ​​anomaly ZI or Z2.

Claims

DEMANDS 1. A method for automatically repairing damage to a layer comprising metallic cables of a tire carcass (9), characterized in that it comprises the following steps: Detection (step RI) of the position of at least one anomaly zone (ZI; Z2) and one healthy zone (Z0) on an image of at least one cable (C) of the ribbon cable; Categorization (step R2) of the anomaly zone (ZI; Z2) detected according to two types of anomaly zone, an anomaly zone intended to be brushed (Zl) if gum (G) is present in the vicinity of said anomaly zone (Zl), and an anomaly zone intended to be ground (Z2) for any other anomaly zone; Selection (step R3) of the repair tool (15) between a brush and a grinding wheel depending on the category of the anomaly zone (Z1; Z2) detected; and Repair (step R7) of cable (C) by using the repair tool (15) selected on said cable (C).

2. A method according to claim 1 wherein the step (R2) of categorizing the anomaly zone (Zl; Z2) categorizes said anomaly zone (Zl; Z2) as an anomaly zone intended to be brushed (Zl) if gum (G) is present within 5 cm, preferably within 2 cm, or even more preferably in contact with said anomaly zone (Zl).

3. A method according to any one of claims 1 and 2, wherein the detection step (RI) is followed by a grouping step (R4) of several detected anomaly zones (Z1; Z2) into a primary anomaly zone when said anomaly zones (Z1; Z2) are located at a distance less than a predefined distance from each other.

4. A method according to any one of claims 1 to 3, comprising, before the repair step (R7), a step (R5) of enlarging an anomaly zone (Z1; Z2) to a predefined minimum size when said anomaly zone has a size less than said predefined minimum size.

5. A method according to any one of claims 1 to 4, wherein the repair step (R7) is implemented so that the repair tool (15) has a translational movement (M1) along the longitudinal direction of the cable (C) from the sound area (ZO) to the anomaly area (Z1; Z2), as well as a rotational movement (M2) about an axis orthogonal to the translational movement and in the opposite direction to a rolling direction (M3) of the repair tool (15) on said cable (C).

6. A method according to any one of claims 1 to 5, wherein the brush comprises rigid metal bristles adapted to remove gum located on cables from the ply of the tire carcass, the grinding wheel being made of carbide or stone.

7. A method according to any one of claims 1 to 6, wherein the detection step (RI) comprises the detection of the position of at least one anomaly zone (ZI; Z2), preferably comprising a structural anomaly, by machine learning and optionally by visible, multispectral or infrared color image processing, the image of at least one cable of the ribbon cable being a visible, multispectral or infrared color image.

8. Method according to any one of claims 1 to 7, comprising prior to a step (RO) of acquiring an image, preferably a secondary image in visible colors, multispectral or infrared, of at least one cable (C) of the ribbon cable.

9. A method according to any one of claims 1 to 8, comprising, after the detection step (RI), a registration step (R6) of a primary image of the tire acquired by a main imaging system (5) fixed relative to the tire carcass (9) with the image, preferably the secondary image in visible colors, multispectral or infrared, acquired by a secondary imaging system (7) mobile relative to the tire carcass (9) and whose field of observation is included in the field of observation of the main imaging system (5), the registration step (R7) being implemented by applying a registration homography to said main image or to said secondary image.

10. Industrial repair system (1) comprising a fixed primary imaging system (5) including one or two cameras adapted to acquire a three-dimensional point cloud, a mobile secondary imaging system (7), preferably with a visible color, multispectral, or infrared sensor, the field of view of which is included within the field of view of the primary imaging system, an effector (13) including a repair tool (15), the repair system (1) including means (3) for implementing the method according to any one of claims 1 to 9, the effector (13) being driven by the primary imaging system (5) to perform step (R7) of repair. 1 1. Computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the process according to any one of claims 1 to 9.

Images