Method for checking a part

Abstract

The invention relates to a method for checking a part (10) with reference to a scale comprising a plurality of material integrity grades and at least one reference image (24) associated with each grade, the method comprising: - obtaining an image (20) of the part (10) in at least one imaging direction (12); - obtaining a mask (22) of the part (10); - applying the mask (22) to the at least one reference image (24) in at least one position and at least one orientation in order to obtain at least one comparative image (30) associated with the grade of the corresponding reference image (24); - for each comparative image (30), calculating (32) a metric representative of the difference in material integrity between the comparative image (30) and the image (20) of the part (10); - on the basis of the calculated metric, assigning (36), to the part (10), the material integrity grade for which the difference in material integrity is minimised.

Description

Part inspection process Technical field

[0001] This presentation concerns the field of industrial quality, and more specifically a process for controlling a part, particularly in terms of the integrity of the part's material, sometimes known as "material health". This process can be applied to parts in all sectors of activity, particularly aeronautics. Prior art

[0002] Assessing the quality of a part requires an objective reference. To this end, standards, such as ASTM E2660 (“E2660-17: Standard Digital Reference Images for Investment Steel Castings for Aerospace Applications”) in the field of aerospace casting, have been established to provide a scale comprising several quality levels, typically several material integrity grades, and at least one reference image associated with each grade. Thus, by visually comparing an image of the part to be evaluated with these reference images, an operator can, following the requirements of the appropriate standard, estimate the quality of the part.

[0003] In this document, the quality of the material is assessed based on the presence of casting defects, and classified into 8 grades. “Grade 1” corresponds to a healthy material, without material defects, and “Grade 8” corresponds to very degraded material health.

[0004] However, visual estimation of part quality by an operator is based solely on an empirical approach, and is therefore non-deterministic. This approach is therefore subjective, which can lead to poor estimates, and relatively slow, which limits the transposition of this approach to larger-scale applications.

[0005] There is therefore a need for a new type of part inspection process. Statement of the invention

[0006] To this end, the present disclosure relates to a method for controlling a part with reference to a scale comprising several grades of material integrity and at least one reference image associated with each grade, the method comprising: - obtaining an image of the part according to at least one imaging direction; - obtaining a mask of the part; - applying the mask to the at least one reference image according to at least one position and at least one orientation in order to obtain at least one comparative image associated with the grade of the corresponding reference image; - for each comparative image, the calculation of a metric representative of the difference in material integrity between the comparative image and the image of the part; - based on the calculated metric, assigning the part the grade for which the difference in material integrity is minimized.

[0007] As previously stated, the scale may define several material integrity grades. Each grade is associated with at least one reference image representative of the integrity of the material for said grade. In this disclosure, and unless otherwise indicated, by "a" or "I" reference image is meant "at least one" or "the at least one" or "each" reference image. More generally, by "an" or "I" element is meant "at least one" or "the at least one" or "each" element. Conversely, the generic use of the plural may include the singular.

[0008] Reference images can be images of the same type as the part image being obtained. Conversely, to allow for a suitable comparison, the imaging technique for the part is chosen to provide a result of the same nature as the reference images.

[0009] The imaging direction, where applicable, refers to the direction in which the image of the part is taken. For example, for a two-dimensional image, the imaging direction is a direction orthogonal to the image plane. Obtaining an image may include acquiring an image at from the part or retrieving an image of the part previously acquired and recorded, typically on a recording medium.

[0010] Similarly, obtaining a mask of the part may include acquiring the mask from the part or retrieving a previously acquired and recorded mask, typically on a recording medium.

[0011] A part mask is a filter configured to, given a source image showing the part, let through a portion of the source image that is the same shape as the part and mask the rest of the source image, or vice versa. Thus, the part mask can reproduce the contours of the part.

[0012] The part mask can be a mask of the previously obtained part image. More generally, the part mask can show the part in the same imaging direction as the part image.

[0013] In general, there is no guarantee that the part image is of comparable dimensions and shapes to those of the reference images. In order to be able to compare the part image with the reference images, the part mask is applied to the reference images, like a stencil, to extract reference images from the so-called comparative images, which have a shape and dimensions comparable to those of the part image (or even exactly those of the part). Thus, the method can be applied to parts of any shape and size.

[0014] Each comparative image remains associated with the grade of the reference image (e.g. a reference image from the ASTM grading scale) from which it was derived. In other words, the comparative image inherits the grade of the reference image from which this comparative image was obtained.

[0015] A metric is then calculated, for each comparative image, to quantify the difference in material integrity between the comparative image and the part image. The metric can be based on any characteristic of the images related to material integrity, for example, defect size, defect spacing, defect density or homogeneity, etc. Other examples will be given later.

[0016] Image operations, such as calculating a metric, can be performed by associating one or more values ​​with each cell elementary value of the image, for example at each pixel. The values ​​can be representative of a color, a gray level, etc.

[0017] The metric considered is not absolute but reflects the difference between the part image and a comparative image in terms of material integrity. The metric therefore aims to quantify how similar the part image and the comparative image are. The metric generally returns a value. The metric can take into account several criteria, which can be weighted relative to each other, if necessary.

[0018] Based on the metric calculated for all comparative images, the part grade can be determined as the grade of the comparative image for which the difference in material integrity is minimized. Indeed, the metric makes it possible to determine, among the comparative images, the one whose part image is most similar in terms of material integrity. This comparative image is therefore representative of the material integrity of the part, which is why the part is assigned the grade associated with this comparative image.

[0019] The proposed method therefore makes it possible to estimate in a deterministic, reliable and objective manner the grade of a part, and therefore its material integrity, by calculating a metric with reference to comparative images comparable to the image of the part. In addition, such a method can be easily automated, which allows significant time savings.

[0020] The steps of the control process can be implemented by computer.

[0021] In some embodiments, the image of the part is obtained by a non-destructive imaging method. Thus, any production part can be inspected without impacting its properties, and not just a few samples that will inevitably be discarded later.

[0022] For example, the image of the part can be an X-ray, for example a two-dimensional X-ray. The X-ray can be performed using X-rays or any radiation suitable for the structure and materials of the part.

[0023] In some embodiments, the inspection method includes obtaining an image of the part along multiple imaging directions, and the grade is assigned to the part based on the grades assigned for each of the imaging directions. Indeed, an inspected part is not necessarily isotropic in terms of material integrity. Considering multiple imaging directions minimizes the influence of selecting an imaging direction, and thus better estimates the material integrity of the part. The inspection process is therefore more robust.

[0024] Optionally, the grade assigned to the part is an average of the grades assigned for each of the imaging directions or the grade for which the difference in material integrity is minimized over the different imaging directions. Depending on what is being sought and the properties that we are trying to control, we can in fact be interested in the average grade of a part, or the grade that is most likely regardless of the imaging direction considered.

[0025] In some embodiments, the mask is applied to the at least one reference image in a plurality of positions and / or a plurality of orientations, whereby a plurality of comparative images is obtained for the at least one reference image. In other words, several comparative images may be obtained from the same reference image. The reference images may not be homogeneous, and / or the mask may be relatively small compared to a reference image. By applying the mask in a plurality of positions and / or a plurality of orientations, the influence of edge effects in the positioning of the mask on the reference image is minimized. This makes it possible to better take into account the information contained in the reference image. The control method is therefore more robust, because the metric is calculated on a larger and more representative base of comparative images.

[0026] In some embodiments, the mask is applied according to a random selection method such as a Monte Carlo method. Random selection methods, and more particularly the Monte Carlo method, are statistical methods, known per se, which make it possible to randomly select several values ​​according to a given probability law, for example a uniform probability law. In this case, the random selection method can make it possible to randomly select positions and orientations of the mask relative to the reference image considered. Thanks to these provisions, the plurality of comparative images can be obtained without bias, which further contributes to the robustness of the control method.

[0027] In some embodiments, the metric compares at least one of Shannon entropy and the size of a defect area between the image comparative and the part image. Shannon entropy, known as such in information theory, quantifies the amount of information contained in an input signal such as an image. The underlying idea is that two images are similar in terms of material integrity if they contain similar amounts of information in terms of the amount of defects and disruption of their structure.

[0028] Furthermore, the size of a defective area may refer to a real or effective dimension of the defect, for example an apparent side or an apparent radius of the defect, i.e. the square root of the area of ​​the defect or the radius of the circle with the same area as the defect.

[0029] Shannon entropy and the size of a defective area are relatively simple quantities to calculate, which therefore allow efficient and robust automation of the inspection process. Furthermore, when used in combination, Shannon entropy and the size of a defective area provide complementary information to estimate the difference between the part image and the comparative image. The proposed metric is therefore an effective measure of the difference between two images.

[0030] In some embodiments, the metric is defined by M f H > f A sont weights associated respectively with Shannon entropy and the size of the defective area, HQ measures Shannon entropy, x ref represents the comparative image, X RX represents the image of the part, A ref represents the size of a defective area on the comparative image and A RXrepresents the size of a defective area on the part image. The weights can be taken equal or modulated according to the importance given to this or that criterion depending on the properties that one seeks to quantify.

[0031] In some embodiments, the size of a defective area is measured by the number of pixels having a value exceeding a threshold representative of healthy material. Typically, for an area measurement, the number of contiguous pixels (connected by arc) having a value exceeding said threshold is counted in two dimensions.

[0032] Thus, the size of the defective area is easy to estimate automatically. The representative threshold can be a value representative of a certain color or a certain gray level, or more generally of any quantity encoded by the image, as explained previously. In order to have a value adapted to the representative images provided with the scale, the representative threshold can be determined from the reference image representing the healthiest grade, for example as being equal to the average value of this reference image added (or subtracted) from one standard deviation, or even three standard deviations.

[0033] In some embodiments, the control method comprises adjusting at least one of the resolution, the color distribution, and the thickness of the material represented for the image of the part relative to the at least one reference image. The control method therefore makes it possible to transform the image of the part to place it in conditions similar to the conditions in which the reference images were obtained, so that the comparison (via the calculation of metrics) is as reliable as possible.

[0034] In some embodiments, the adjustment comprises assigning, to a material pixel of the part image, a value determined from a value of the healthy material on one of the at least one reference image. By associating a value determined from a healthy material value on a reference image, for example on the reference image corresponding to the healthiest grade, each material pixel value of the part image is virtually transformed into the same thickness and material as the reference one. This procedure directly converts the value ranges (e.g., gray levels) of the part image to that of the reference image and also geometrically transforms the part into a representation of the parts from which the reference images originate. This makes the comparison between the part image and the comparative images even more reliable.

[0035] In some embodiments, obtaining the image of the part includes obtaining a three-dimensional image of the part comprising a plurality of voxels, assigning a first value to the healthy material voxels of the plurality of voxels and a second value to the defect voxels of the plurality of voxels, and two-dimensionally projecting the three-dimensional image along the at least one imaging direction, wherein a value of a pixel of the resulting image is calculated based on the values ​​of the voxels that are projected onto that pixel.

[0036] A voxel is in three dimensions what a pixel is in two dimensions, namely an elementary cell of an image. The projection can be performed along the imaging direction. The resulting image, or projection image (i.e., the part image), is obtained by taking into account the voxels that overlap along the imaging direction to form a single pixel of the part image. The two-dimensional projection results in a two-dimensional image.

[0037] A voxel is determined to represent healthy material or a defect depending on its value and the imaging technique used. For example, a person skilled in the art knows that, for a given imaging technique, a void is represented by a high value or a low value. A threshold may be considered to distinguish between voxels of healthy material and voxels of defect, the threshold being able to have some or all of the characteristics previously mentioned.

[0038] Thanks to these characteristics, it is possible to obtain an image, typically in two dimensions (2D), from a three-dimensional (3D) image of a part for which a 2D imaging method is not applicable or not desired. In particular, this obtaining method makes it possible to obtain 2D images of digital parts modeled in 3D.

[0039] In some embodiments, the first value is a non-zero constant, e.g., 1, and / or the second value is zero.

[0040] In some embodiments, the control method comprises identifying the defect voxels by segmenting the three-dimensional image. Image segmentation, for example so-called semantic segmentation, is a technique known per se and using, for example, deep learning models. The identification of the defect voxels can thus be automated.

[0041] In other embodiments, particularly when the part is a digital part in which the defects have been digitally placed, the defect voxels may be known by construction.

[0042] In some embodiments, the value of the aforementioned pixel is equal to the sum of the values ​​of the voxels that are projected onto this pixel. The sum is an approximation of the Beer-Lambert law, which reflects the absorption of an imaging ray passing through the part, for small thicknesses. The fact that the value of the pixel is equal to the sum of the values ​​of the voxels that are projected onto it therefore provides both a simple and physically relevant method for calculating the image of the part.

[0043] In some embodiments, the three-dimensional image of the part is a three-dimensional tomography. Tomography, for example X-ray, is a technique known per se for obtaining three-dimensional images.

[0044] In some embodiments, the inspection method includes validating or rejecting the part based on the grade assigned to the part. Typically, if the grade exceeds a certain threshold, the part may be discarded, and otherwise retained. Thus, production quality can be effectively maintained.

[0045] In a particular embodiment, the various steps of the control method are determined by computer program instructions. In other words, the control method can be implemented by computer.

[0046] Consequently, the present disclosure also relates to a program set comprising instructions for executing the steps of the control method described above when said program set is executed by at least one computer or microprocessor.

[0047] This program package may use any programming language, and may be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0048] This disclosure also relates to an information medium readable by a computer or by a microprocessor, and comprising instructions of a set of programs as mentioned above.

[0049] The information carrier may be any entity or device capable of storing the entire program. For example, the carrier may include a storage medium, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a floppy disk or a hard disk.

[0050] Furthermore, the information carrier may be a transmissible medium such as an electrical or optical signal, which may be conveyed via an electrical or optical cable, by radio or by other means. The program according to the present disclosure may in particular be downloaded from a network such as the Internet.

[0051] The present disclosure also relates to a method for imaging a part, comprising obtaining a three-dimensional image of the part comprising a plurality of voxels, assigning a first value to the healthy material voxels of the plurality of voxels and a second value to the defect voxels of the plurality of voxels, and two-dimensionally projecting the three-dimensional image along the at least one imaging direction, wherein a value of a pixel of the resulting image is calculated based on the values ​​of the voxels that are projected onto that pixel. The imaging method may have some or all of the features previously mentioned with respect to the inspection method. Brief description of the drawings

[0052] Other characteristics and advantages of the subject of the present disclosure will emerge from the following description of embodiments, given as non-limiting examples, with reference to the appended figures.

[0053] Figure 1 is a general diagram of a control method according to one embodiment.

[0054] Figure 2 represents a step of projecting a three-dimensional image into a two-dimensional image. Detailed description

[0055] A method for inspecting a part according to one embodiment is described with reference to Figures 1 and 2. The inspection method aims to quantify the material integrity of the part with reference to a scale comprising several material integrity grades. The material integrity scale used is, for example, the ASTM grade scale (see ASTM E2660 standard).

[0056] Figure 1 shows a part 10 whose integrity is to be checked, in the form of a mechanical test piece. However, the control method applies to any type of part, regardless of its shape, dimensions, material, function, etc. In particular, but not exclusively, the part 10 may be a casting made of a metal alloy. The part 10 may be a part from the aeronautics field, for example an aircraft engine part. Examples include aircraft engine bearings or parts of bladed wheels such as low pressure turbine distributors.

[0057] The control method comprises obtaining an image 20 of the part 10 along at least one imaging direction 12. In this case, the aim is to obtain an image of the part 10 that can be compared to reference images associated with the material integrity grades of the aforementioned scale. In the event that these reference images are two-dimensional, the image 20 of the part 10 may also be two-dimensional. However, more generally, the image 20 of the part 10 may have the same dimensionality as the reference images.

[0058] The imaging direction 12 can be chosen randomly or according to a predetermined program.

[0059] According to one example, the image 20 of the part 10 is obtained by a non-destructive imaging method such as an X-ray, in particular a 2D X-ray. However, any other method may be used, in particular a method similar to the method used to obtain the reference images.

[0060] For example, as an alternative to 2D radiography, it is possible to first obtain a three-dimensional image of the part 10, for example by 3D tomography, then to carry out a projection of this three-dimensional image according to the imaging direction 12 in order to obtain the image 20 of the part 10. 3D tomography can offer better image quality than 2D radiography.

[0061] As indicated previously, the control method comprises obtaining a mask 22 of the part 10. The mask 22 can be obtained as a mask of the image 20 of the part 10. The mask 22 can reproduce, in the dimensionality of the image 20 or, better, in the dimensionality of the reference images, the contours of the part 10. Obtaining such a mask 22 can be carried out by image processing techniques known, as such, to those skilled in the art.

[0062] As previously indicated, in the aforementioned scale, at least one reference image is associated with each grade 1, 2, ..., N of material integrity. The reference image reflects the typical material integrity observed for a part having the corresponding grade. As illustrated in Figure 1, the image of the part 20 is compared with each grade 1, 2, ..., N. To do this, the mask 22 is applied to the reference images associated with at least two of the grades, preferably to each of the grades. For the sake of brevity, the following description and Figure 1 detail the application of the mask 22 to a reference image associated with one of the grades, but the same operations can be performed for all the reference images associated with a given grade, and this for all the desired grades in the aforementioned scale.

[0063] Thus, with reference to Figure 1, the mask 22 is applied to a reference image 24 according to at least one position and at least one orientation, or even according to a plurality of positions and / or a plurality of orientations. In the present disclosure, the position refers to the relative coordinates of a given point (arbitrarily chosen) of the mask 22 with respect to the reference image 24, while the orientation quantifies the angle of rotation of the mask 22 around said given point with respect to a starting orientation (arbitrarily chosen) of the mask 22. In this case, Figure 1 represents the same reference image 24 on which the mask 22 is applied at two different pairs (position; orientation). From one application of the mask 22 to another, at least one of the position and the orientation of the mask 22 with respect to the reference image 24 may vary.The number of applications of the mask 22 per reference image 24 may vary, however it is desirable that the applications of the mask 22 are well distributed over the entire reference image 24, typically covering at least half of the reference image 24 in total. In this way, the loss of information from the reference image 24 is limited and the impact of the choice of the position or orientation of the mask 22 is reduced.

[0064] According to one example, the mask 22 may be applied to the image several times according to a random selection method such as a Monte Carlo method. The random selection method may be used to determine successive positions and / or successive orientations. Geometric constraints may also be imposed to prevent the mask 22, at the determined position and orientation, from leaving the reference image 24.

[0065] Each application of the mask 22 to the reference image 24 makes it possible to obtain a comparative image 30 associated with the corresponding position and orientation. The comparative image 30 is an image of the same shape as the part 10 or as its image 20, thanks to the mask 22, the level of material integrity of which reflects the grade of the reference image 24 from which it comes. In in other words, the comparative image 30 can be associated with the grade of the corresponding reference image 24.

[0066] Furthermore, as illustrated in FIG. 1, when the mask 22 is applied according to a plurality of positions and / or a plurality of orientations, a plurality of comparative images 30 can be obtained from the same reference image 24.

[0067] To make the comparison between the comparative images 30 and the image 20 of the part 10 more reliable, an adjustment 14 can be made to obtain the image 20 of the part 10. The adjustment 14 comprises a digital transformation applied (for example to a provisional image of the part 10) to obtain the image 20. For example, the adjustment 14 relates to the resolution or the color distribution of the obtained image 20. Alternatively or in addition, the image 20 can be modified to neutralize the difference in thickness between the part 10 and the samples which were used to obtain the reference images 24.

[0068] According to one example, the reference images 24 may be obtained from flat samples having a given thickness, known in the scale considered (for example, given by a standard such as the ASTM standard). Conversely, the part 10 may not be flat but for example cylindrical (in particular axisymmetric) or other. It is possible to apply to the image a geometry correction function (for example a sinusoid to transform a cylinder with a circular section into a plate). Alternatively, in particular when the geometry correction is more complex to formulate, it is possible to adjust the image 20 of the part on the basis of the value of the healthy material in the reference image.

[0069] More specifically, the adjustment 14 may comprise the assignment, to a material pixel of the image 20 of the part 10, of a value determined from a value of the healthy material on one of the at least one reference image 24.

[0070] According to an example, one can proceed as follows: one creates a 3D mask of the part 10 and one counts the number of voxels Ni along the imaging direction 12, at each location i transverse to this imaging direction 12. One then determines a constant ai such that the product Ni x ai is equal to the average value of a pixel of healthy material, said average value that can be determined with reference to the reference image 24 of the grade with the best material integrity.

[0071] The value ai is then assigned to the material voxels of part 10 at location i. To account for the variance on the reference image 24, it is possible to add to the image 20 of part 10 a noise matrix with the same variance as the reference image 24 considered (reference image representative of healthy material, preferably). The noise can follow a normal distribution. The defect voxels are assigned a different value, for example zero.

[0072] It is therefore noted that the adjustment 14 varies for each position i, which makes it possible to virtually transform any geometry into a plate. It is within the reach of those skilled in the art to adapt this method if the samples serving as a basis for the reference images 24 have a geometry other than a plate.

[0073] In Figure 1, image 20 represents the image of part 10 after adjustment 14, adjustment 14 being able to be carried out on a provisional image of part 10.

[0074] The control method further comprises, for at least one comparative image and preferably for each comparative image 30, the calculation 32 of a metric M(XRX, X ref ) representative of the difference in material integrity between the comparative image 30, noted X ref , and image 20 of part 10, noted XRX.

[0075] The metric can compare at least one of Shannon entropy and the size of a defective area between the comparative image and the part image. However, other measures can be incorporated, as an alternative or in addition, to the metric.

[0076] In an example that combines these two measures, the metric might be of the form: where f H , f Aare weights respectively associated with the Shannon entropy and the size of the defective area, H(.) measures the Shannon entropy of an image (here comparative image, or part image), A ref represents the size of a defective area on the comparative image and A RX represents the size of a defective area on the part image. Preferably, are percentages such as f H + fA = 100%. For example, we choose values ​​equal to 50% for these two weights.

[0077] Shannon entropy can be calculated in a known way.

[0078] The size of a defective area may be equal to the number of pixels, preferably consecutive, having a value exceeding a threshold representative of a healthy material. For example, starting from a first pixel whose value exceeds said threshold, all the pixels which are contiguous to this first pixel and whose value also exceeds said threshold are counted, and this in all dimensions of the image (here, for example, in two dimensions). The number of pixels thus obtained is representative of an area of ​​the defect. The size of a defective area may correspond directly to this number of pixels, or to an effective dimension such as the apparent side of the defective area (square root of the area of ​​the defect) or the apparent radius of the defective area (radius of the circle with the same area as the determined number of pixels).

[0079] The metric calculation 32 returns, for each comparative image 30, a value reflecting the level of difference between the image 20 of the part 10 and the comparative image 30 considered, it being recalled that each comparative image 30 is also associated with a material integrity grade. Thus, the different values ​​of the metric reflect the difference between the image 20 of the part 10 and the different grades of the scale.

[0080] At this stage, the metric values ​​obtained are however dependent on the imaging direction 12 selected initially. To reduce this dependence, it is possible to carry out iterations 34 of the steps previously described by modifying the imaging direction 12, and thus applying the steps previously described for each imaging direction 12 chosen. Thus, the control method can comprise obtaining an image 20 of the part 10 according to several imaging directions 12. Several images 20 are then obtained to which all or part of the steps previously described are applied.

[0081] The imaging directions 12 may be selected randomly or in any other manner, for example in an equidistant manner. Each iteration 34 may be followed by a rotation 16 of the part 10.

[0082] Once the metric has been calculated, if applicable for all the desired imaging directions, the control method proceeds to assign 36, to the part 10, the grade for which the difference in material integrity is minimized. Typically, the smallest value obtained from the metric is selected and the part 10 is assigned the grade of the comparative image 30 for which this smallest metric value was obtained. When there are several imaging directions, the grade is preferentially assigned to the part according to the grades assigned for each of the imaging directions. When several comparative images 30 are considered for the same grade, the values ​​of the metric obtained for said same grade can be combined, for example via the calculation of an average for the grade considered. Other combinations are however possible, including a calculation of a minimum or maximum among the metric values ​​obtained for said same grade.

[0083] Optionally, the control method may further comprise a step 38 of validation or rejection of the part 10 depending on the grade assigned to the part 10. Validation, a fortiori in the case where the imaging method is non-destructive, reinforces the quality of the industrial process in which the part 10 is used. For example, a threshold grade may be predetermined depending on the application of the part 10, and step 38 consists of verifying whether or not the grade calculated for the part 10 exceeds said threshold grade. Depending on the case, the part may be rejected for insufficient material integrity or, on the contrary, validated for acceptable material integrity.

[0084] The above description applies to real parts and can be transposed to digital parts (such as digitally generated synthetic microstructures). For digital parts in particular, traditional imaging methods may not be applicable and other methods may be necessary to obtain an image of the part along an imaging direction.

[0085] Thus, in one example, obtaining an image of the part may comprise obtaining a three-dimensional image of the part, assigning a first value to the healthy material voxels and a second value to the defect voxels, and projecting the three-dimensional image along the at least one imaging direction. The principle underlying this method is illustrated in Figure 2.

[0086] The three-dimensional image 40 of the part may be a three-dimensional tomography, either actually obtained by 3D tomography, or simulated on the basis of a digital model of the part. For the sake of simplification but without loss of generality, the three-dimensional image 40 is here schematized as a cylinder.

[0087] In this three-dimensional image 40, it is possible to know which voxels represent a healthy material and which voxels represent a defect: either this information is given following the construction of the three-dimensional image (typically from a digital model), or the identification of the defect voxels can be obtained otherwise, for example by a method of semantic segmentation of the defects in the three-dimensional image 40.

[0088] The voxels of healthy material are then assigned a first value, for example a non-zero constant, and the defect voxels a second value, for example a zero value. This can reflect the fact that defects are most often characterized by an absence of material. More practically, this can reflect the fact that in grayscale, material appears gray while defects, often characterized by a void, appear black.

[0089] The three-dimensional image 40 is then projected along the imaging direction 12 as illustrated in FIG. 2, as if performing 2D imaging of the part. For example, the value of a pixel in the resulting image is calculated based on the values ​​of the voxels that are projected onto that pixel.

[0090] In this context, the Beer-Lambert law states that the intensity of a monochromatic beam passing through a material decreases with increasing depth of the inspected material. This intensity reduction, quantified by a decreasing exponential, can be approximated for assumed small thicknesses by a sum. Therefore, the intensity through a material can be rewritten as the sum of material voxels along the imaging direction 12. More precisely, the value of a pixel in the resulting image of the projection (i.e., image 20 of part 10) can be equal to the sum of the values ​​of the voxels that are projected onto that pixel. The void voxels, since they are assigned a zero value, do not contribute to the attenuation of the simulated imaging beam.

[0091] For the sake of completeness, it is noted that the assumption of linear variation of attenuation excludes beam hardening and scattering effects. However, the consequences of these effects are assumed to be negligible at first order.

[0092] Thus, the proposed control method not only allows assigning a grade to a (real) material part for its industrial validation, but also to assign a grade to a digital part, for example in order to annotate part images (or even parts directly) to constitute a learning base for a machine learning model, with the aim of better predicting the service life of parts, for example the fatigue life. This avoids long and costly physical test campaigns.

[0093] Although the present description refers to specific exemplary embodiments, modifications may be made to these examples without departing from the general scope of the invention. Furthermore, individual features of the various embodiments illustrated or mentioned may be combined in additional embodiments. Therefore, the description and drawings should be considered in an illustrative rather than restrictive sense.

Claims

CLAIMS

1. A method of inspecting a part (10) with reference to a scale comprising a plurality of material integrity grades and at least one reference image (24) associated with each grade, the method comprising the following computer-implemented steps: - obtaining an image (20) of the part (10) according to at least one imaging direction (12); - obtaining a mask (22) of the part (10); - applying the mask (22) to the at least one reference image (24) according to at least one position and at least one orientation in order to obtain at least one comparative image (30) associated with the grade of the corresponding reference image (24); - for each comparative image (30), the calculation (32) of a metric representative of the difference in material integrity between the comparative image (30) and the image (20) of the part (10); - based on the calculated metric, assigning (36) to the part (10) the material integrity grade for which the material integrity difference is minimized.

2. A method of inspection according to claim 1, wherein the image (20) of the part (10) is obtained by a non-destructive imaging method, optionally wherein the image (20) of the part (10) is an X-ray.

3. A method of inspection according to claim 1 or 2, comprising obtaining an image (20) of the part (10) according to several imaging directions (12), and in which the grade is assigned to the part (10) according to the grades assigned for each of the imaging directions (12).

4. A testing method according to claim 3, wherein the grade assigned to the part (10) is an average of the grades assigned for each of the imaging directions (12) or is the grade for which the difference in integrity of the material is minimized over the different imaging directions (12).

5. A control method according to any one of claims 1 to 4, wherein the mask (22) is applied to the at least one reference image (24) according to a plurality of positions and / or a plurality of orientations, whereby a plurality of comparative images (30) is obtained for said at least one reference image (24).

6. A control method according to claim 5, wherein the mask (22) is applied according to a random drawing method such as a Monte Carlo method.

7. A testing method according to any one of claims 1 to 6, wherein the metric compares at least one of Shannon entropy and the size of a defective area between the comparative image (30) and the image (20) of the part (10); optionally wherein the metric is defined by weights associated with Shannon entropy and the size of the defective area, H(.) measures Shannon entropy, x ref represents the comparative image (30), X RX represents the image (20) of the part (10), A ref represents the size of a defective area on the comparative image (30) and A RX represents the size of a defective area on the image (20) of the part (10).

8. A control method according to any one of claims 1 to 7, wherein obtaining the image (20) of the part (10) comprises obtaining a three-dimensional image (40) of the part (10) comprising a plurality of voxels, assigning a first value to the healthy material voxels of the plurality of voxels and a second value to the defect voxels of the plurality of voxels, and projecting the three-dimensional image (40) along the at least one imaging direction (12), wherein a value of a pixel of the resulting image (20) is calculated as a function of the values of the voxels that are projected onto that pixel.

9. Control method according to any one of claims 1 to 8, comprising a step of validation or rejection (38) of the part (10) depending on the grade assigned to the part (10).

10. Program set comprising instructions for executing the steps of the control method according to any one of claims 1 to 9 when said program set is executed by at least one computer or microprocessor.

Images