Method and apparatus for detecting defects on tyres in a tyre production process

1. A method for detecting defects on a tyre in a tyre production process, comprising:

a) providing a tyre;

b) acquiring a three-dimensional image of a surface portion of the tyre;

c) generating, as a function of the acquired image, a plurality of values indicating a measure of a height profile of the surface portion of the tyre;

d) interpolating the plurality of values of the measure of the height profile and using a consensus interpolation algorithm to generate a line indicating an estimation of a reference height profile of the surface portion of the tyre;

e) calculating, as a function of the plurality of values of the measure of the height profile and of the estimation of the reference height profile, a height profile of possible defects in the surface portion of the tyre; and

f) comparing values of the height profile of possible defects with respect to a threshold value to detect possible defects in the surface portion of the tyre.

2. The method according to claim 1 , wherein said portion of the tyre extends along at least a part of a circumferential surface of the tyre around a rotation axis thereof, and wherein the method further comprises:

subdividing said tyre portion into a plurality of arc-shaped sections;

subdividing said three-dimensional image into a plurality of three-dimensional images corresponding to said plurality of arc-shaped sections; and

iteratively repeating from c) to e) so as to generate a plurality of height profiles of possible defects corresponding to said plurality of arc-shaped sections.

3. The method according to claim 2 , further comprising generating said height profile of possible defects as a function of said plurality of height profiles of possible defects corresponding to said plurality of arc-shaped sections.

4. The method according to claim 1 , further comprising:

subdividing said portion of the tyre into a plurality of substantially annular bands having a substantially constant width; and

repeating from b) to f) for each band of the plurality of bands.

5. The method according to claim 4 , wherein two contiguous bands are at least partially circumferentially overlapped on each other.

6. The method according to claim 1 , further comprising:

receiving a configuration height profile of a portion of the tyre indicating a position of expected elements on the portion of the tyre; and

comparing the height profile of possible defects with respect to the configuration height profile, so as to remove said expected elements from the height profile of possible defects.

7. The method according to claim 6 , further comprising:

receiving a reference tyre substantially defect-free and calculating, by means of from b) to f), said configuration height profile, wherein said expected elements are detected as defects on said reference tyre.

8. A non-transitory computer readable medium having a program comprising software code portions adapted to perform at least c), d), e), f) of the method according to claim 1 , when said program is run on at least one computer.

9. A process for producing tyres, comprising:

building green tyres;

moulding and curing the green tyres; and

controlling the green and/or cured tyres according to the method of claim 1 .

10. The method according to claim 1 , wherein the consensus interpolation algorithm is chosen from:

RANdom SAmple Consensus—RANSAC;

PROgressive SAmple Consensus—PROSAC;

randomized RANSAC;

progressive RANSAC;

Maximum Likelihood EStimation SAmple Consensus—MLESAC;

Maximum A Posteriori EStimation SAmple Consensus—MAPSAC;

N Adjacent Points random consensus—NAPSAC;

IMPortance SAmpling Consensus—IMPSAC; and

robust filtering by consensus—KALMANSAC.

11. The method according to claim 10 , wherein the consensus interpolation is of RANdom SAmple Consensus—RANSAC type.

12. An apparatus to detect defects on a tyre in a tyre production line, comprising:

a support and movement member having a support adapted to support a tyre and to rotate said tyre around a rotation axis thereof;

a light source configured to emit a light radiation for illuminating a portion of the surface of the tyre during rotation thereof;

at least one camera configured to acquire a three-dimensional image of the surface portion of the tyre during rotation thereof; and

a processing unit configured to:

generate, as a function of the acquired image, a plurality of values indicating a measure of a height profile of the surface portion of the tyre;

interpolate the plurality of values of the measure of the height profile and using a consensus interpolation algorithm, to generate a line indicating an estimation of a reference height profile of the surface portion of the tyre;

calculate, as a function of the plurality of values of the measure of the height profile and of the estimation of the reference height profile, a height profile of possible defects in said surface portion of the tyre; and

compare values of the height profile of possible defects with respect to a threshold value to detect possible defects in the surface portion of the tyre.

13. A tyre production line, comprising:

a working station;

a moulding and curing station; and

a control station comprising an apparatus to detect defects on tyres according to claim 12 .

14. The apparatus according to claim 12 , wherein the processing unit is configured to interpolate the plurality of valves of the measure of the height profile using the consensus interpolation algorithm chosen from:

RANdom SAmple Consensus—RANSAC;

PROgressive SAmple Consensus—PROSAC;

randomized RANSAC;

progressive RANSAC;

Maximum Likelihood EStimation SAmple Consensus—MLESAC;

Maximum A Posteriori EStimation SAmple Consensus—MAPSAC;

N Adjacent Points random consensus—NAPSAC;

IMPortance SAmpling Consensus—IMPSAC; and

robust filtering by consensus—KALMANSAC.

15. The apparatus according to claim 14 , wherein the consensus interpolation is of RANdom SAmple Consensus—RANSAC type.