A fast and automatic detection method, system and detection equipment for ceramic substrate

Abstract

The present application relates to the technical field of ceramic substrate detection, and specifically to a method, system and detection equipment for rapid automatic detection of ceramic substrates, the method comprising obtaining sample defects of unqualified substrates; characterizing the sample defects, wherein the characteristics at least include the marked position; finding the correlation of the sample defects according to the characteristics of the sample defects, and obtaining multiple defect groups; counting the marked positions of all sample defects; identifying local areas where sample defects are distributed more as target detection areas; performing defect detection on the target detection area to obtain partial defects; performing comparison in the defect groups, and finding the defect groups corresponding to the partial defects as target defects. The present application utilizes finding defect groups with correlation from sample defects, and identifying local areas where defects are distributed more, finding partial defects in the local areas where defects are distributed more, and identifying the target defects according to the correlation of the defect groups.

Description

Technical Field

[0001] The present application relates to the technical field of ceramic substrate detection, and in particular to a rapid and automatic detection method, system and detection equipment for ceramic substrates. Background Art

[0002] The ceramic substrate has good welding performance, and the welding void rate is less than 5%. The ceramic substrate has a thicker copper layer, which can bear a high current load. Under the same cross-section, it only needs 12% of the conductive width of the usual PCB board, and can transmit more power per unit volume, improving the reliability of the system and equipment. It is precisely because of the various excellent properties of the ceramic substrate that the ceramic substrate is widely used in the preparation of various types of high-power semiconductors, especially IGBT packaging materials. The ceramic substrate is the internal substrate of the IGBT module based on the EASY package. The performance of the ceramic substrate determines the final performance of the IGBT module. Before the final test of the IGBT module, the ceramic substrate needs to be tested in the middle of the process. After the test is qualified, the finished product is plastic-sealed to ensure that the performance of the ceramic substrate is intact during the IGBT module test, and to prevent the ceramic substrate from being damaged during the IGBT module test, resulting in invalid IGBT module test, wasting detection time and cost.

[0003] The more common practice in the existing technology is to use appearance inspection or mechanical property inspection. Machine vision AI inspection is also unable to identify the void defects in the internal interlayer, and mechanical property inspection is a destructive test. After the inspection, it is difficult to continue to use the ceramic substrate. The ultrasonic scanning microscope SAT combines the characteristics of high precision and non-destructive testing, and has a very high sensitivity to interstitial defects such as bubbles and voids that appear in the interlayer of the ceramic substrate. High-precision super-scan imaging can be performed on the internal bonding surface of the ceramic substrate.

[0004] Although the ultrasonic scanning microscope SAT can accurately detect defects in ceramic substrates, it is slow, which consumes a lot of time, especially when dealing with multiple ceramic substrates being spliced ​​or when re-inspection is required with high precision.

[0005] Therefore, there is currently a lack of a method, system and detection equipment that can quickly detect defects in ceramic substrates. Summary of the invention

[0006] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0007] The following description and accompanying drawings fully illustrate specific embodiments of the present invention so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The examples represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. The scope of the embodiments of the present invention includes the entire scope of the claims, and all available equivalents of the claims. In this article, each embodiment may be represented individually or generally by the term "invention", which is only for convenience, and if more than one invention is disclosed in fact, it is not intended to automatically limit the scope of the application to any single invention or inventive concept. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, without requiring or implying any actual relationship or order between these entities or operations. Moreover, the terms "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method or device including the elements. The various embodiments herein are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, since they correspond to the method part disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0008] In order to solve the above technical problems, the embodiments of the present disclosure provide a method, system and device for rapid and automatic detection of ceramic substrates, which are used to solve the problem of slow detection speed of ceramic substrates in the prior art.

[0009] The disclosed embodiment provides a method for rapid and automatic detection of ceramic substrates, comprising: obtaining sample defects of unqualified substrates; characterizing the sample defects, wherein the characteristics at least include marked positions; finding correlations among the sample defects based on the characteristics of the sample defects to obtain multiple defect groups; counting the marked positions of all sample defects; identifying local areas where sample defects are more distributed as target detection areas; performing defect detection on the target detection areas to obtain partial defects; comparing the characteristics of the partial defects in the defect groups to find the defect groups corresponding to the partial defects as the target defects.

[0010] Preferably, the features of the sample defects are clustered, and similar sample defects are classified as the same sample defects.

[0011] Preferably, the sample defects are processed into a grid and the positions in the grid are marked.

[0012] Preferably, the characteristics also include type and shape.

[0013] Preferably, the feature further comprises a texture.

[0014] In a second aspect, an embodiment of the present disclosure provides a rapid automatic detection system for ceramic substrates, comprising:

[0015] The defect group generation module is configured to obtain sample defects of unqualified substrates; describe the sample defects with characteristics, wherein the characteristics at least include marked positions; find the correlation of the sample defects according to the characteristics of the sample defects, and obtain multiple defect groups;

[0016] The target detection region generation module is configured to count the annotated positions of all sample defects and identify the local area where the sample defects are more distributed as the target detection area;

[0017] The target defect recognition module is configured to perform defect detection on the target detection area, obtain partial defects, compare the characteristics of the partial defects in the defect group, and find the defect group corresponding to the partial defects as the target defect.

[0018] Preferably, the rapid automatic detection system for ceramic substrates further comprises:

[0019] The clustering module is configured to cluster the features of the sample defects and classify similar sample defects as the same sample defects.

[0020] Preferably, the rapid automatic detection system for ceramic substrates further comprises:

[0021] The gridding processing module is configured to perform gridding processing on sample defects and mark the positions in the grid.

[0022] In a third aspect, an embodiment of the present disclosure provides a detection device, which is applied to the above-mentioned rapid automatic detection method of the ceramic substrate.

[0023] The embodiments of the present disclosure provide a method, system and equipment for rapid and automatic detection of ceramic substrates, the method comprising: obtaining sample defects of unqualified substrates; characterizing the sample defects, wherein the characteristics at least include marked positions; finding correlations among the sample defects based on the characteristics of the sample defects to obtain multiple defect groups; counting the marked positions of all sample defects; identifying local areas where sample defects are more distributed as target detection areas; performing defect detection on the target detection area to obtain partial defects; comparing the characteristics of the partial defects in the defect group, finding the defect group corresponding to the partial defects as the target defect.

[0024] The disclosed embodiment utilizes the method of finding a defect group with correlation from sample defects, identifying a local area where defects are more distributed, finding some defects in the local area where defects are more distributed, and identifying the target defect according to the correlation of the defect group.

[0025] In this way, more defects can be analyzed based on the correlation of defect groups by identifying local defects, thereby achieving rapid inspection of ceramic substrates. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0027] Figure 1 is a schematic diagram of a rapid and automatic detection method for a ceramic substrate provided by an embodiment of the present disclosure;

[0028] Figure 2 is a defect schematic diagram of a ceramic substrate provided by an embodiment of the present disclosure;

[0029] Figure 3 It is a schematic diagram of a rapid automatic detection system for ceramic substrates provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0031] The following description and accompanying drawings fully illustrate the specific embodiments of the present application so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The examples represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. The scope of the embodiments of the present application includes the entire scope of the claims, and all available equivalents of the claims. In this article, each embodiment may be represented individually or generally by the term "application", which is only for convenience, and if more than one application is disclosed in fact, it is not intended to automatically limit the scope of the application to any single application or application concept. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, without requiring or implying that there is any actual relationship or order between these entities or operations. Moreover, the terms "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method or device including the elements. The various embodiments herein are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, since they correspond to the method part disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0032] In addition, the terms "disposed", "connected", and "fixed" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present disclosure can be understood according to specific circumstances.

[0033] The more common practice in the existing technology is to use appearance inspection or mechanical property inspection. Machine vision AI inspection is also unable to identify the void defects in the internal interlayer, and mechanical property inspection is a destructive test. After the inspection, it is difficult to continue to use the ceramic substrate. The ultrasonic scanning microscope SAT combines the characteristics of high precision and non-destructive testing, and has a very high sensitivity to interstitial defects such as bubbles and voids that appear in the interlayer of the ceramic substrate. High-precision super-scan imaging can be performed on the internal bonding surface of the ceramic substrate.

[0034] Although the ultrasonic scanning microscope SAT can accurately detect defects in ceramic substrates, it is slow, which consumes a lot of time, especially when dealing with multiple ceramic substrates being spliced ​​or when re-inspection is required with high precision.

[0035] In order to solve the above technical problems, the embodiments of the present disclosure provide a method, system and device for rapid automatic detection of ceramic substrates, which are used to solve the problems of low efficiency and poor stability of manual detection of ceramic substrate defects in the prior art.

[0036] See also Figure 2 , a method for rapid automatic detection of a ceramic substrate is provided for an embodiment of the present disclosure, comprising:

[0037] S10, obtaining sample defects of unqualified substrates.

[0038] S20, describing the sample defects by features, wherein the features at least include a marked position.

[0039] In practical applications, the defects in the image are accurately segmented and annotated so that the characteristics of each defect can be analyzed separately. The characteristics can also include any one or more of type, shape or texture. For location, the coordinates of the defect center and the distance and relative orientation between them are calculated; for shape, geometric features such as area, perimeter, aspect ratio, circularity, etc. are extracted; for type, the defects are classified and described according to their appearance, color, texture and other characteristics.

[0040] Furthermore, the features of the sample defects are clustered, and similar sample defects are classified as the same sample defects.

[0041] In a preferred embodiment, the sample defects are processed into a grid, and the grid is used as a position for marking, so as to facilitate marking the position of the ceramic substrate.

[0042] S30, according to the characteristics of the sample defects, find the correlation of the sample defects and obtain multiple defect groups.

[0043] Ceramic powders such as alumina, aluminum nitride, or doped zirconium oxide are cast and sintered to form ceramic substrates, and then metallized to prepare ceramic substrates. Because of its good stability, large current carrying capacity, high electrical insulation and high thermal conductivity. Due to the presence of tiny defects in a part of the production equipment during the production of ceramic substrates, the same type of defects may occur at the same position each time they are produced, or, under the action of periodic forces, defects may occur at specific angles. For example, for each ceramic substrate produced, a little offset and pressure will accumulate in the production process, but for every 20 ceramic substrates produced, there will be a rebound pressure release of offset and pressure, resulting in defects in the ceramic substrate. The cause of each defect is the same offset and rebound pressure release of pressure, so the cause of each defect in the ceramic substrate is the same, that is, the same defect distribution will be generated as a defect distribution combination. In addition, the inhomogeneity of the material itself or the characteristics of the internal structure may show regular defects during machining or use. The material may have texture or fiber orientation, and when subjected to force or processing, it is easy to crack or defect along a specific direction.

[0044] Therefore, there will be correlation between defects. For example, when defect stripe A appears, defect stripe B will inevitably appear at an interval of 20 mm. The two defect stripes will appear at the same time, and the positions are relative. Defect stripe A and defect stripe B are combined into a defect group. The position of the defect group may be uncertain, and may appear at a fixed position or randomly.

[0045] It should be understood that the number of defects in a defect group can be one or more. When the number of defects is one, then there is no defect with correlation. When the number of defects is multiple, if any one of the defects appears, then the other defects in the same defect group must appear. There is correlation between the multiple defects in the defect group. This correlation includes at least position correlation, and may also include any one or more of type correlation, shape correlation and texture correlation. See Figure 2 , is a schematic diagram of a defect group. The defect group consists of copper defects, one is circular and the other is oblong. The circular copper defect and the oblong copper defect appear simultaneously, and the positions are 2 mm apart.

[0046] For position correlation, the defect center and the distance and relative orientation between defects are calculated; for shape, geometric features such as area, perimeter, aspect ratio, circularity, etc. are extracted; and for type, defects are classified into defects such as voids, copper traces, and ceramic cracks.

[0047] The correlation analysis method can be to perform statistical analysis on the extracted features, or it can be to process the characteristic data of the defects and discover potential correlation patterns using pattern recognition algorithms such as cluster analysis and principal component analysis.

[0048] S40, counting the marked positions of all sample defects.

[0049] S50, identifying a local area where sample defects are more distributed as a target detection area.

[0050] It should be understood that S40 and S50 are for obtaining the area where defects are most likely to occur. In practical applications, after the ceramic substrate area is gridded, all gridded areas are sorted, and a preset number of areas with higher rankings are selected as target detection areas.

[0051] S60, performing defect detection on the target detection area to obtain partial defects.

[0052] Since the probability of defects appearing in the target detection area is higher, it is easier to obtain defects.

[0053] S70, comparing the features of the partial defects in the defect groups, finding the defect group corresponding to the partial defects as the target defect.

[0054] The partial defects obtained in the target detection area can be used to find the corresponding defect group by using the correlation in the defect group. That is, the defect group can be inferred from the partial defects. For example, a defect group is x defect, y defect and z defect. When x defect is identified, y defect and z defect can be inferred accordingly.

[0055] Then, as an example, the defect distribution combination of the ceramic substrate after the grid can be the first defect position (x, y), the second defect position (x+2, y+4) and the third defect position (x+9, y+4). When the second defect position (x+2, y+4) is identified, the first defect position (x, y) and the third defect position (x+9, y+4) must appear. Just scanning the second defect position (x+2, y+4) can identify the corresponding defect group.

[0056] It should be understood that the disclosed embodiment can be used for rapid inspection of ceramic substrates, but since it is not a complete area scan, and since more defects are inferred from the defective area, some defects may be missed. In practical applications, it is more suitable for large ceramic substrate inspection, ceramic substrate combination inspection or re-inspection.

[0057] The embodiment of the present disclosure provides a rapid automatic detection system for ceramic substrates, comprising:

[0058] The defect group generation module is configured to obtain sample defects of unqualified substrates; describe the sample defects with characteristics, wherein the characteristics at least include marked positions; find the correlation of the sample defects according to the characteristics of the sample defects, and obtain multiple defect groups;

[0059] The target detection region generation module is configured to count the annotated positions of all sample defects and identify the local area where the sample defects are more distributed as the target detection area;

[0060] The target defect recognition module is configured to perform defect detection on the target detection area, obtain the characteristics of the initial defect, compare the characteristics of the initial defect in the defect group, and find the defect group corresponding to the initial defect as the target defect.

[0061] In a preferred embodiment, the rapid automatic detection system for ceramic substrates further comprises:

[0062] The clustering module is configured to cluster the features of the sample defects and classify similar sample defects as the same sample defects.

[0063] In a preferred embodiment, the rapid automatic detection system for ceramic substrates further comprises:

[0064] The gridding processing module is configured to perform gridding processing on sample defects and mark the positions in the grid.

[0065] The embodiment of the present disclosure provides a detection device applied to the above-mentioned rapid automatic detection method of the ceramic substrate.

[0066] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0067] Those skilled in the art will appreciate that the systems and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the above-described devices, apparatuses, and systems may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0068] The flowchart and block diagram in the accompanying drawings show the possible architecture, functions and operations of the device, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by dedicated hardware-based devices that perform the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A rapid and automatic detection method for ceramic substrates, Features: include: Obtain sample defects of unqualified substrates; Describing the sample defects by features, wherein the features at least include the marked positions; According to the characteristics of sample defects, the correlation of sample defects is found to obtain multiple defect groups, where the defect group is a single defect or a combination of multiple defects. If the defect group is a single defect, the corresponding single defect has no correlation with other defects and will appear alone; if the defect group is a combination of multiple defects, all defects in the corresponding defect group will appear at the same time; Count the marked locations of all sample defects; Identify the local area where sample defects are more distributed as the target detection area; Perform defect detection on the target detection area to obtain some defects; The features of some defects are compared in the defect group, and the defect group corresponding to the partial defects is found as the target defect.

2. The rapid automatic detection method for ceramic substrates according to claim 1, Features: Also includes: The features of sample defects are clustered, and similar sample defects are classified as the same sample defects.

3. The rapid automatic detection method for ceramic substrates according to claim 1, Features: The sample defects are gridded and the positions are marked in the grid.

4. The rapid automatic detection method for ceramic substrates according to claim 1, Features: The characteristics also include type and shape.

5. The rapid automatic detection method of ceramic substrate according to claim 4, Features: The features also include texture.

6. A fast and automatic detection system for ceramic substrates, Features: include: a defect group generation module configured to obtain sample defects of unqualified substrates; Describing the sample defects by features, wherein the features at least include the marked positions, finding the correlations of the sample defects according to the features of the sample defects, and obtaining multiple defect groups, wherein the defect group is a single defect or a combination of multiple defects, and if the defect group is a single defect, the corresponding unique defect will appear alone; if the defect group is a combination of multiple defects, all defects in the corresponding defect group will appear at the same time; The target detection region generation module is configured to count the annotated positions of all sample defects and identify the local area where the sample defects are more distributed as the target detection area; The target defect recognition module is configured to perform defect detection on the target detection area, obtain partial defects, compare the characteristics of the partial defects in the defect group, and find the defect group corresponding to the partial defects as the target defect.

7. The rapid automatic detection system for ceramic substrates according to claim 6, Features: include: The clustering module is configured to cluster the features of the sample defects and classify similar sample defects as the same sample defects.

8. The rapid automatic detection system for ceramic substrates according to claim 6, Features: include: The gridding processing module is configured to perform gridding processing on sample defects and mark the positions in the grid.

9. A detection device, Features: A rapid and automatic detection method for a ceramic substrate as claimed in any one of claims 1 to 5.

Images