METHOD AND DEVICE FOR PRODUCING A PRODUCT AND COMPUTER PROGRAM PRODUCT

Abstract

The disclosure relates to a method and a device for producing a product and to a computer program product. The product is produced in at least one production step. A quality control check is optionally carried out after at least one of the production steps to determine a quality index of the product in question. To save on the quality control check, a quality indicator of the product in question is determined using production data. The production data are advantageously provided by sensors. The quality indicator of the product in question may be calculated using an adaptive algorithm. The adaptive algorithm may be taught and/or improved using quality indices of a quality control unit and the corresponding production data. The adaptive algorithm may be taught with the aid of a further computing unit, in particular in a cloud.

Claims

1. A method comprising: producing a circuit board in at least one production step; providing production data during each production step of the at least one production step, wherein the production data is a position of an applied solder paste on the circuit board, a deviation of the applied solder paste in relation to a target position or a target pattern, a thickness of a layer of the applied solder paste, a temperature or an air humidity of an environment of the circuit board, or a combination thereof; calculating a quality indicator based on the respective production data; and associating the quality indicator with the circuit board,

2. The method of claim 1, wherein the respective quality indicator is associated with the circuit board with aid of a database or a marking on the circuit board,

3. The method of claim 1, wherein, after the at least one production step, a quality control check takes place, and wherein, during the quality control check, in each case a quality index is associated with the circuit board.

4. The method of claim 3, wherein the quality indicator is determined with aid of a learning-capable algorithm, wherein the learning-capable algorithm is teachable by a comparison of production data, the quality indices, and optionally the respective quality indicator.

5. The method of claim 4, wherein the learning-capable algorithm is taught such that the respective quality indicator corresponds to the respective quality index of the circuit board.

6. The method of claim 1, wherein the quality indicator and/or a quality index of the circuit board is displayed to a user, and wherein, based on the quality indicator, a selection of what is to happen to the circuit board is configured to be provided by the user.

7. The method of claim 6, further comprising: determining whether a quality control check of the circuit board is to take place based on the quality indicator and/or the selection by the user.

8. The method of claim 1, wherein at least one sensor determines at least one environmental influence, and wherein the at least one sensor provides the at least one environmental influence as a portion of the production data.

9. The method of claim 1, wherein the production data comprises a position and a characteristic of a fastening device, wherein the characteristic is the position and a quantity of the applied solder paste or a position and/or quantity of an insulation material.

10. The method of claim 4, wherein the learning-capable algorithm is based upon a decision tree, a neural network, a support vector analysis, or a combination thereof.

11. The method of claim 3, wherein the quality control check comprises an optical or an X-ray optical method and/or an electrical check of the circuit board.

12. The method of claim I, wherein, with aid of a conversion module, production data from a plurality of different sensors is convertible to a common data type.

13. The method of claim 1, wherein, based on the calculated quality indicator, a production step is adapted.

14. A computer program product for execution on a computing unit, wherein the computing unit is configured to: produce a circuit board in at least one production step; provide production data during each production step of the production of the circuit board, wherein the production data is a position of an applied solder paste on the circuit board, a deviation of the applied solder paste in relation to a target position or a target pattern, a thickness of a layer of the applied solder paste, a temperature or an air humidity of an environment of the circuit board, or a combination thereof; calculate a quality indicator based on the respective production data; and associate the quality indicator with the circuit board.

15. An apparatus for producing a circuit board, the apparatus comprising: a production unit or a plurality of production units for producing the circuit board; a computing unit for calculating and/or providing a quality indicator of the circuit board; a data acquisition device for providing production data for the computing unit, wherein the calculation and/or the provision of the quality indicator comprises: the production of the circuit board; the provision of the production data during each production step of at least one production step of the production of the circuit board, wherein the production data is a position of an applied solder paste on the circuit board, a deviation of the applied solder paste in relation to a target position or a target pattern, a thickness of a layer of the applied solder paste, a temperature or an air humidity of an environment of the circuit board, or a combination thereof; a calculation of a quality indicator based on the respective production data; and an association of the quality indicator with the circuit board.

16. The apparatus of claim 15, further comprising: a quality control unit configured for determining a quality index of the circuit board.

17. The apparatus of claim 16, wherein the computing unit and the quality control unit are configured cooperative or are operable cooperatively such that the quality indicator provided by the computing unit and the quality index provided by the quality control unit assume a same value.

18. The apparatus of claim 15, wherein the data acquisition device is configured as a sensor.

19. The apparatus of claim 15, wherein the computing unit is coupled to a decentralized server or a cloud, and wherein the decentralized server or the cloud is configured for teaching a learning-capable algorithm.

20. The apparatus of claim 15, wherein the apparatus is configured to produce the circuit boards with components, wherein the production data is provided to describe an application of the solder paste to the circuit board, and wherein the quality indicator and/or a quality index is provided for describing an adequate contacting of the components with the circuit board after the application of the solder paste to the circuit board.

21. The apparatus of claim 17, wherein the quality index of the circuit board is confirmable with aid of the quality control unit via an optical and/or X-ray optical method.

22. The apparatus of claim 15, wherein a first production unit of the plurality of production units is provided for applying the solder paste to the circuit board, wherein a second production unit of the plurality of production units is provided for equipping the circuit board with components, wherein a third production unit of the plurality of production units is configured as an oven, and wherein the oven is configured to form an electrical connection of the circuit board with a component of the components with aid of the solder paste.

23. The apparatus of claim 15, wherein the production unit is configured for insulating an electrical conductor, via a winding for an electric machine, and wherein a quality index and/or the quality indicator are each a measure for an insulation of the electrical conductor.

24. The apparatus of claim 15, wherein the apparatus comprises a first quantity of production units with a respective maximum production capacity of a second quantity of circuit boards per time unit, wherein the apparatus comprises a third quantity of quality control units for determining the respective quality indices of the respective circuit boards, wherein a monitoring capacity of the third quantity of quality control units per time unit forms a fourth quantity, wherein the circuit board of the first quantity and the second quantity is smaller than the fourth quantity.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0156] The disclosure will now be described and explained in greater detail making reference to the drawings. The embodiments illustrated in the drawings are merely exemplary and in no way restrict the disclosure. Individual features shown in the drawings may be combined into new embodiments. In the drawings:

[0157] FIG. 1 depicts an exemplary apparatus.

[0158] FIG. 2 depicts an exemplary method.

[0159] FIG. 3 depicts an exemplary learning-capable algorithm.

[0160] FIG. 4 depicts a further exemplary apparatus.

[0161] FIG. 5 depicts a further exemplary apparatus.

DETAILED DESCRIPTION

[0162] FIG. 1 depicts an exemplary apparatus. The apparatus includes three production units PE1, PE2, PE3. The apparatus further includes a quality control unit QME. In the first production unit PE1, a first production act P1 takes place. During the first production act P1, a fastening component or device BM is applied to a product P. A possible fastening component or device BM is an adhesive or a solder paste. A first sensor S1 acquires the location and the quantity of the fastening component or device BM applied to the product P. The first sensor S1 provides the production data X1 of the first production act P1 to the computing unit RE. The product P is then passed to a second production unit PE2.

[0163] A second sensor S2 serves herein for determining an environmental influence such as a temperature or the air humidity. Advantageously, an acquisition of the environmental influence takes place insofar as the environmental influence influences one of the production acts P1, P2, P3.

[0164] In the second production unit PE2, a second production act P2 takes place. In the second production act P2, the product P is further processed. A quality index QI is also associated with the product P. The quality index QI is provided by the computing unit RE and is associated with the product P during its passage through the production acts. The product P is passed on to a third production unit PE3. In the third production unit PE3, a third production act P3 takes place. A third sensor S3 is associated with the third production unit PE3.

[0165] After the execution of the third production act P3, a quality control check QM takes place in a quality control unit QME. The quality control unit QME includes a further sensor which is configured to check the quality index QI of the respective product P. The quality control check QM is performed here with the aid of an X-ray analysis. In this case, the further sensor is configured as an X-ray detector.

[0166] Advantageously, with the aid of the quality index QI associated with the product P, it may be decided whether or not a quality control check QM in the quality control unit QME is necessary for the product P after its passage through the third production unit PE3.

[0167] FIG. 2 depicts an exemplary method. In a first method act V1, production data x1, . . . , xn from sensors S1, S2, S3 is provided to a computing unit RE. Optionally, in the first method act V1, the production data x1, . . . , xn is converted to a uniform data type. In a second method act V2, with the aid of the learning-capable algorithm A, the quality index QI is calculated from the production data x1, . . . , xn. The quality index QI is associated with the respective product P, during the production of which the production data x1, . . . , xn has been determined. The association of the quality index QI with the product P may take place through entry into a database (not shown) or through a marking of the quality index QI on the product P itself. In a third method act V3, on the basis of the quality index QI, it is decided whether or not a quality control check QM takes place for the respective product P. In the decision of whether a quality control check QM takes place, a user B may also confirm, on the basis of a quality index QI displayed to him or her, the execution of a quality control check QM.

[0168] FIG. 3 depicts an exemplary learning-capable algorithm A. The algorithm A serves for calculation of the quality index QI from the production data x1, . . . , xn. The production data x1, . . . , xn is determined during the production of the respective product by the sensors S1, S2, S3. After the calculation of the respective quality index QI, this quality index QI is associated with the product P.

[0169] Optionally, with the aid of a conversion module Par, a conversion of the production data x1, . . . , xn into a uniform data type takes place. The production data x1, . . . , xn in the uniform data type is fed to the learning-capable algorithm A.

[0170] In order to improve the learning-capable algorithm A, teaching of the learning-capable algorithm advantageously takes place. The teaching of the learning-capable algorithm A may take place in a further computing unit CL, for example, a cloud. In order to improve the learning-capable algorithm A, measured production data x1, . . . , xn is compared with quality indices QI which have been determined in a quality control check QM. Both the production data x1, . . . , xn and also the associated quality indices QI are provided to a neural network, an algorithm on the basis of artificial intelligence, or a support vector algorithm. The learning-capable algorithm A is improved by the comparison of the production data X1, . . . , xn determined with the aid of sensors and the quality index QI which is also determined experimentally. A regular exchange of the learning-capable algorithm A of the computing unit RE with the trained, learning-capable algorithm A from the further computing unit CL may take place.

[0171] FIG. 4 depicts a further exemplary apparatus. The apparatus includes two production lines HL1, HL2 and a quality control unit QME.

[0172] The first production line HL1 and the second production line HL2 each include three production units PE1, PE2, PE3. The production units PE1, PE2, PE3 each serve for producing products P.

[0173] The production units PE1, PE2, PE3 each provide production data x1, . . . , xn to a computing unit RE. The computing unit RE serves for determining a quality indicator QI for the respective product P. The quality indicator QI is associated with the respective product P. The association advantageously takes place with the aid of a database DB.

[0174] A learning-capable algorithm A, (e.g., in the form of a computer program product), is installed on the computing unit RE. With the aid of the learning-capable algorithm A, the computing unit provides a quality indicator QX for the respective product.

[0175] The learning-capable algorithm A may be taught with the aid of a further computing unit CL. The further computing unit CL is advantageously at least partially linked in a data-conducting manner to the computing unit RE. The computing unit RE provides the production data x1, . . . , xn to the further computing unit CL.

[0176] The products P from the first production line HL1 and the second production line HL2 are provided to a quality control unit QME.

[0177] The quality control unit QME serves for quality control checking QM of individual products P. The quality control unit QME then associates a quality index QX with a portion of the products P. The quality control unit QME provides the respective quality index QX for the respective product to the further computing unit CL. The further computing unit CL advantageously serves for a comparison of the quality indicators QI with the respectively determined quality index QX.

[0178] Through the comparison of the quality index QX with the corresponding quality indicator QI, the further computing unit CL may check how good the determination of the quality indicator QI is.

[0179] FIG. 5 depicts a further exemplary apparatus. The apparatus includes a first quantity a of production units PE1, PE2, PE3. In the example shown, the first quantity a is two. The first quantity of production units PE1, PE2, PE3 is configured for producing a second quantity b of products P per time unit t. The second quantity is shown here as two, e.g., a production unit PE1, PE2, PE3 may produce a maximum of two products per time unit t.

[0180] For example, the three production units PE1, PE2, PE3 jointly produce six products per time unit t.

[0181] The six products P per time unit t are provided to a third quantity c of quality control units QME. The quality control units QME may carry out, for example, just one quality control check QM of a fourth quantity d of products P in the time unit t. In this example, the fourth quantity is four. Thereafter, a larger quantity of products P, specifically the product of the first quantity a and the second quantity b of products P, pass through a quality control check QM in one of the quality control units QME. The product of the first quantity a and the second quantity b is advantageously greater than the overall capacity of the quality control units QME. The capacity is specifiable by the fourth quantity d. In the example shown here, the fourth quantity is four and is thus smaller than the product of the first quantity a and the second quantity b (a*b=6).

[0182] By virtue of the disclosure, with the aid of the calculation and the association of the respective quality indicator with the respective product P, the productivity of the apparatus may advantageously be increased.

[0183] Summarizing, the disclosure relates to a method and an apparatus for producing a product P, as well as a computer program product. The product P is produced in at least one production act P1, P2, P3. Optionally, after at least one of the production acts P1, P2, P3, a quality control check QM takes place to determine a quality index QX of the respective product P. In order to spare the quality control check QM, a determination of a quality indicator QI of the respective product P takes place on the basis of production data x1, . . . , xn. The production data x1, . . . , xn is advantageously provided by sensors S1, S2, S3. The calculation of the quality indicator QI of the respective product P advantageously takes place with the aid of a learning-capable algorithm A. The learning-capable algorithm A may be taught and/or improved with quality indices QX from a quality control check QM and the corresponding production data x1, . . . , xn. The teaching of the learning-capable algorithm A may take place with the aid of a further computing unit CL, in particular, in a cloud.

[0184] It is to be understood that the elements and features recited in the appended claims may be combined in different ways to produce new claims that likewise fall within the scope of the present disclosure. Thus, whereas the dependent claims appended below depend from only a single independent or dependent claim, it is to be understood that these dependent claims may, alternatively, be made to depend in the alternative from any preceding or following claim, whether independent or dependent, and that such new combinations are to be understood as forming a part of the present specification.

[0185] Although the disclosure has been illustrated and described in detail with the exemplary embodiments, the disclosure is not restricted by the examples disclosed and other variations may be derived therefrom by a person skilled in the art without departing from the protective scope of the disclosure.