CN-114283111-B - Qualitative or quantitative characterization of the coating surface

CN114283111BCN 114283111 BCN114283111 BCN 114283111BCN-114283111-B

Abstract

The invention relates to a method for qualitatively and/or quantitatively characterizing a coating surface, comprising providing a defect recognition program (124) designed to recognize a type of defect (1204,1206,1306,1308) in the coating surface, the defect recognition program comprising a predictive model which has been trained on the basis of training images (604, 606) acquired within a predetermined distance range and/or within a predetermined image acquisition angle range relative to the coating surface depicted in the training images, determining by the defect recognition program whether at least one camera (134) operatively connected to the defect recognition program is located within the predetermined distance range and/or within the predetermined image acquisition angle range relative to the currently presented coating surface, generating a feedback signal on the basis of the determination whether an adjustment of the position of the at least one camera is required for the camera to be located within the predetermined distance range and/or within the predetermined image acquisition angle range, and/or automatically adjusting the relative distance of the at least one camera and the coating surface such that the camera position is within the predetermined distance range from the coating surface, and/or automatically adjusting the angle of the at least one camera, such that the camera position is within a predetermined image acquisition angle range, allowing the camera to acquire a digital image (604,606,1202) of the presented coating surface only if the camera is within the predetermined distance range and/or the image acquisition angle range, processing (102) the digital image (604,606,1202) of the coating surface (162-168) by a defect recognition program for recognizing defects of the coating surface, outputting (104) a representation of the coating surface by the defect recognition program, the representation being calculated in relation to the recognized defects of the coating surface.

Inventors

Philip isken
Sandra bitorf
Oliver Kroll
Claudia Bramlag
Marcus Vogel
S. Silber
Gaitano Brenda
Olivia Louis
Daniel. Huck

Assignees

赢创运营有限公司
赢创运营有限公司

Dates

Publication Date: 20260421
Application Date: 20210916
Priority Date: 20200917

Claims (20)

1. A method for qualitatively and/or quantitatively characterizing a surface of a coating, the method comprising: Providing a defect recognition program (124) designed to recognize a coating surface defect type (1204,1206,1306,1308), the defect recognition program comprising a predictive model that has been trained on training images (604, 606) acquired within a predetermined distance range and/or within a predetermined image acquisition angle range relative to the coating surface depicted in the training images; Providing a data storage medium, wherein a plurality of coating surface defect types are each stored in association with a predetermined distance range of distances of at least one camera from the coating surface and/or in association with one or more predetermined image acquisition angle ranges, the predetermined image acquisition angle ranges and/or distance ranges stored in association with a particular defect type being angle ranges and/or distance ranges that allow acquisition of digital images of the coating surface, which allow the defect identification program to identify the defect type in the digital images of the coating surface; Determining at least one coating surface defect type to be identified; for each of the determined at least one coating surface defect type to be identified: Automatically identifying one of the predetermined distance ranges and/or one of the one or more predetermined image acquisition angle ranges stored in association with the determined defect type; Determining, by the defect recognition program, whether at least one camera (134) operatively connected to the defect recognition program is within the predetermined distance range and/or the predetermined image acquisition angle range relative to the currently presented coating surface, whereby the defect recognition program uses the identified predetermined distance range and/or the identified predetermined image acquisition angle range to determine whether the camera is within the predetermined distance range or the image acquisition angle range; According to the determination result Generating a feedback signal whether an adjustment of the position of the at least one camera is required so that the camera is located within the predetermined distance range and/or the predetermined image acquisition angle range, and/or Automatically adjusting the relative distance of the at least one camera and the coating surface such that the camera position is within a predetermined distance range from the coating surface and/or automatically adjusting the angle of the at least one camera such that the camera position is within a predetermined image acquisition angle range; Allowing the camera to acquire digital images (604,606,1202) of the presented coating surface only if the camera is within a predetermined distance range and/or image acquisition angle range; processing (102) a digital image (604,606,1202) of the coating surface (162-168) by the defect recognition program for recognizing defects in the coating surface; a representation of the coating surface is output (104) by the defect recognition program, the representation being calculated in relation to the identified coating surface defects.
2. The method according to claim 1, comprising calculating (106) a measure (632,634,1402) for the identified defect by means of a defect identification program, wherein the characterization of the coating surface is calculated in relation to a qualitative and/or quantitative characterization of the measure.
3. The method according to claim 2, The measure is a quantitative measure selected from the group consisting of defect area, number of bubbles or depressions observed in the digital image (604,606,1202), maximum size, minimum size and/or average size of bubbles or depressions in the digital image (604,606,1202), and/or The measure is a qualitative measure of a type of defect selected from the group consisting of pit defects, scratch defects, adhesion failure defects, crocodile defects, bleeding defects, blister defects, bloom defects, tie defects, bubble defects, cathodic disbonding defects, fine crack defects, shrinkage cavity defects, wire drawing defects, cracking defects, crazing defects, claw-shaped wrinkle defects, delamination defects, fade defects, skin-falling defects, open bottom defects, heat loss defects, impact damage defects, interlayer offset defects, mud crack defects, orange peel defects, peeling defects, pinhole defects, wavy coating defects, sagging defects, sheet rust defects, point rust defects, rust spot defects, dent defects, settling defects, skinning defects, solvent biting defects, solvent blister defects, stress cracking defects, under-film corrosion defects, wrinkling defects.
4. A method according to one of claims 1 to 3, wherein the predetermined distance range is a distance range between the presented coating surface and the at least one camera, which distance range allows the camera to acquire images with a resolution of at least a predetermined minimum resolution.
5. The method of claim 4, wherein the predetermined minimum resolution is a coating defect type specific minimum resolution.
6. A process according to claim 1 to 3, Automatic adjustment of the relative distance of the at least one camera (134) to the coating surface is performed by automatically changing the position of the at least one camera and/or automatically changing the position of a holder comprising a sample with the coating surface such that the distance between the at least one camera and the coating surface is within a predetermined distance range, and/or Automatic adjustment of the image acquisition angle (1504) relative to the coating surface includes changing the orientation of the at least one camera such that it is oriented relative to the coating surface at an image acquisition angle within a predetermined image acquisition angle range.
7. A method according to any one of claims 1 to 3, wherein, At least one of the one or more surface defect types is stored in association with a predetermined illumination angle range, the predetermined illumination angle range stored in association with a particular defect type being a range of illumination angles of the light source relative to the coating surface, which allows acquisition of a digital image of the coating surface, which allows the defect identification program to identify the defect type in the digital image of the coating surface; for each of the determined at least one coating surface defect type to be identified: automatically identifying one of a range of predetermined illumination angles stored in association with the determined defect type; Determining whether or not to be positioned by one or more light sources relative to the coating surface in such a way that the illumination angle lies within the identified predetermined illumination angle range by a defect identification procedure using the identified predetermined illumination angle range, and If the illumination angle of the one or more light sources is outside the identified predetermined illumination angle range, Positioning the one or more light sources (160) and the coating surface relative to each other such that the illumination angle is within the identified predetermined illumination angle range, and/or A feedback signal is generated that indicates and/or can adjust the positioning of the one or more light sources (160) and the coating surface relative to each other such that the illumination angle is within the identified predetermined illumination angle range.
8. The method of any one of claims 1 to 3, further comprising capturing a digital image of the coating surface using the at least one camera after the coating surface, the at least one camera, and/or the one or more light sources are positioned relative to each other.
9. A method according to any one of claims 1 to 3, the processing of the digital image further comprising: Classifying a digital image by a defect identification program in relation to the type and/or number of surface defects depicted therein and/or image semantic segmentation based on one or more surface defect types depicted therein and/or object detection of defect instances within the image and/or image instance segmentation, whereby one or more labels are automatically assigned to the entire digital image, to a plurality of image areas and/or to individual pixels, each label representing a defect type identified in the digital image, and Outputting the assigned one or more tags.
10. A method according to any one of claims 1 to 3, the defect identification procedure being selected from the group comprising: An application installed on a fixed or portable data processing system (130); An application installed on a portable or stationary device (150) specifically designed for coating surface quality inspection; An application installed on a high-throughput device (244) for automatic or semi-automatic production and/or testing of coatings; A web application downloaded and/or instantiated over a network; a program executed in a browser; A server program instantiated on a server computer, the server program being operatively connected to a client program instantiated on a client data processing system via a network link, the client program being designed to capture the digital image and to provide the image to the server program via the network and/or to display results provided by the server program.
11. A method according to one of claims 1 to 3, the predictive model (M1) being learned from training data (602) comprising training images (604, 606) in a training step performed by a machine learning procedure, the machine learning procedure being designed to identify patterns in digital images, the machine learning procedure being a neural network.
12. The method of one of claims 1 to 3, further comprising generating the predictive model by performing a training step in accordance with training data (602) comprising a training image, the training image comprising a plurality of labels, said labels (616, 618) marking the location and/or type of defects within a coating surface drawn in the training image, the predictive model being trained to identify defect types using back propagation through the marked training image.
13. The method of claim 11, wherein each of the training images has assigned additional data (608, 610) that is processed in the training step to allow the predictive model (M1) to associate additional data with the defect type, the additional data comprising: A quantitative measure of one or more defects plotted in the training image; Optionally also parameters selected from the group consisting of: an indication of one or more components of the coating used to produce a coating surface drawn in the training image; an indication of the absolute or relative amounts of one or more of the components of the coating composition, and/or One or more process parameters characterizing the process of generating the coating composition, including the mixing speed and/or mixing duration of the coating composition, and/or One or more application process parameters characterizing the process of applying the coating composition to the substrate, including the amount of coating composition applied per unit of coating surface area, the type of substrate, and/or the type of application device, and/or System parameters of an imaging system used to acquire training images, the system parameters selected from the group consisting of a type of light source used to illuminate the coating surface, a light source brightness, an illumination angle, a light source wavelength, a type of one or more cameras used to acquire digital images of the coating surface, an image acquisition angle, a position of the one or more cameras.
14. The method of claim 13, wherein the system parameters include at least an illumination angle, an image acquisition angle of the at least one camera, and/or a relative distance of the at least one camera and the coating surface.
15. The method of claim 10, wherein the portable data processing system is a portable telecommunications device.
16. The method of claim 15, wherein the portable telecommunications device is a smartphone.
17. The method of claim 10, wherein the program executed in the browser is a JavaScript program.
18. The method of claim 13, wherein the quantitative measure is the size and/or severity of defects or the number of bubbles.
19. A computer system (224) for qualitatively and/or quantitatively characterizing a surface of a coating, the computer system comprising: A defect recognition program (124) operatively connected to the at least one camera (134) and designed to recognize a coating surface defect type (1204,1206,1306,1308), the defect recognition program comprising a predictive model trained on training images (604, 606) acquired within a predetermined distance range and/or a predetermined image acquisition angle range relative to a coating surface rendered within the training images; A data storage medium, wherein a plurality of coating surface defect types are each stored in association with a predetermined distance range of distances of at least one camera from the coating surface and/or in association with one or more predetermined image acquisition angle ranges, the predetermined image acquisition angle ranges and/or distance ranges stored in association with a particular defect type being angle ranges and/or distance ranges that allow acquisition of digital images of the coating surface, which allow the defect identification program to identify the defect type in the digital images of the coating surface; wherein the defect identification procedure is designed to: Determining at least one coating surface defect type to be identified; for each of the determined at least one coating surface defect type to be identified: Automatically identifying one of the predetermined distance ranges and/or one of the one or more predetermined image acquisition angle ranges stored in association with the determined defect type; Determining whether the at least one camera is located within a predetermined distance range and/or a predetermined image acquisition angle range relative to the currently presented coating surface, whereby the defect recognition program uses the identified predetermined distance range and/or the identified predetermined image acquisition angle range to determine whether the camera is located within the predetermined distance range or the image acquisition angle range; based on the result of the determination: generating a feedback signal whether an adjustment of the position of the at least one camera is required so that the camera is located within the predetermined distance range and/or the predetermined image acquisition angle range, and/or Automatically adjusting the relative distance of the at least one camera and the coating surface such that the camera position is within a predetermined distance range from the coating surface and/or automatically adjusting the angle of the at least one camera such that the camera position is within a predetermined image acquisition angle range; allowing the camera to acquire digital images of the presented coating surface only if the camera is located within a predetermined distance range and/or image acquisition angle range; Processing (102) the digital image (604,606,1202) acquired from the enabled at least one camera to identify one or more defect types therein; A characterization of the coating surface is output (104), which is calculated in relation to the coating surface defects identified during processing by the defect identification procedure.
20. A system, comprising: the computer system of claim 19; The at least one camera, and/or Apparatus (244) for testing components of paints, varnishes, printing inks, grinding resins, pigment concentrates or other coatings, the apparatus comprising: At least one processing station configured to apply one or more coating compositions to at least one surface of the plurality of objects, An automated transport system for transporting coated objects to an image acquisition and analysis system, Wherein the system is designed to automatically acquire images of the coating surface of the plurality of objects and output a representation of the coating surface using the image acquisition and analysis system.

Description

Qualitative or quantitative characterization of the coating surface Technical Field The present invention relates to the identification of coating defects and the characterization of coated surfaces, in particular coated surfaces based on coating compositions for paints, varnishes, printing inks, grinding resins, pigment concentrates or other coating compositions. Background Paint and varnish coatings can have a variety of different defects that can adversely affect the appearance or technical properties of the coated object. Coating defects can be, for example, foam, craters, haze, leveling problems, corrosion, wetting problems, pigment floating (floating), sagging, caking or bubble formation, where a plurality of defects can occur simultaneously and can affect one another. To investigate and avoid these problems, test substrates were coated with the formulation and inspected for defects during formulation development. Depending on the intended application area, different substrates are used, such as wood, plastic, paper/cardboard, glass or metal. Furthermore, different pretreatments of the substrate are possible and pretreatments may complicate matters. Because of the large number of process parameters that are interdependent, the large number of coating compositions, pretreatment methods, and substrate types, it is currently not predictable whether a particular coating composition will provide a coating of acceptable quality when applied to a particular substrate. Thus, the surface quality of the coating can only be determined retrospectively. Currently, defects are assessed visually by humans, such as employees. This purely visual estimate is typically very coarse, highly subjective and difficult to reproduce. Thus, defect identification and coating surface quality assessment may require a great deal of experience from the staff's side, but may vary considerably from person to person, which makes it difficult to compare the results. Furthermore, manual evaluation of the coating surface is time consuming and expensive. SUMMARY The present invention intends to provide an improved method for characterizing surface defects in a coating surface and a corresponding system and the use of the resulting programs and information in a coating composition production environment as specified in the independent claims. Embodiments are given in the dependent claims. Embodiments of the invention may be freely combined with each other as long as they are not mutually exclusive. In one aspect, the present invention relates to a method of qualitatively and/or quantitatively characterizing a surface of a coating. The method comprises the following steps: processing the digital image of the coating surface by a defect recognition program configured to recognize the type of defects of the coating surface, for example by recognizing patterns, each pattern representing one of the types of defects of the coating surface, and -Outputting a representation of the coating surface, the representation being calculated in relation to the coating surface defects identified by the defect identification procedure. Embodiments of the present invention may have the advantage of providing a characterization of the coating surface through a defect identification procedure and thus in a reproducible objective and fast manner. For example, the output characterization may indicate that the coating surface is free of defect type D1, but may contain defect types D2 and D3. The output may also indicate that the coating surface is free of any coating defects. According to other examples, the output may be more specific and also indicate the amount or extent of coating defects, for example by indicating that the surface contains mild defects of the D2 type and severe defects of the D3 type. In other examples, the characterization may include a digital characterization of the extent of the defect and/or an indication of individual pixels in the digital image representing a particular type of defect or a particular instance belonging to a particular defect type. Embodiments of the present invention may have the advantage that the occurrence and/or location of defects in the coating surface are fully automatically detected and used to automatically calculate a coating surface characterization based on the type and/or extent of one or more defects identified in the image analysis program. Thus, a large number of digital images can be fully automatically assessed and annotated with the calculated characterization of the respective depicted coating surfaces. This may be particularly useful in the context of high throughput equipment for testing and/or producing coating compositions. Automated determination of coating surface characterization improves the transparency and reproducibility of the assessment of coating surface quality and other characteristics. Embodiments of the present invention may have the further advantage that automatically identified c