Power semiconductor device appearance detection method, device and equipment
Through the combination of vision detection system and X-ray imaging technology, the problems of low detection efficiency and difficulty in detecting internal defects in the prior art are solved, efficient appearance and internal defect detection are achieved, and product quality is improved.
Patent Information
- Application Number
- CN202411483333.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-01-07
AI Technical Summary
The appearance detection efficiency of existing power semiconductor devices is low, especially for products with large package thickness, it is difficult to detect internal defects, resulting in frequent misjudgment or misjudgment.
The visual detection system is used for multi-angle image acquisition and analysis, combined with X-ray imaging technology, and through surface cleaning processing, image processing and convolutional neural network algorithm, the device is judged to be qualified and screened for qualified and poor products.
It improves the inspection accuracy and efficiency, reduces the workload of staff, avoids misjudgment or misjudgment of internal defects of products, and improves product quality.
Smart Images
Figure CN119269508A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a detection method, and in particular to a method, device and equipment for detecting the appearance of a power semiconductor device. Background Art
[0002] Power semiconductor devices, also known as power electronic devices and power electronic devices, refer to electronic devices that can be directly used in the main circuit for processing electric energy to achieve the conversion or control of electric energy. Such devices play a vital role in the field of power electronics and are mainly used in power electronic control and conversion systems, such as automobiles, mobile phones, power supplies, solar inverters, trains and wind turbines.
[0003] In the production process of power semiconductor devices, in order to ensure the product quality of power semiconductor devices, it is necessary to perform appearance inspection on the power semiconductor devices. The existing appearance inspection of power semiconductor devices mostly relies on staff observation and measurement using tools, and the inspection efficiency is low. At the same time, for products with large package thickness, it is difficult to understand whether there are defects in the internal structure of the product by direct observation. Therefore, a method, device and equipment for appearance inspection of power semiconductor devices are proposed. Summary of the invention
[0004] In view of this, the present invention provides a method, device and equipment for detecting the appearance of a power semiconductor device to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.
[0005] The technical solution of the embodiment of the present invention is implemented as follows: A method for detecting the appearance of a power semiconductor device comprises the following steps: Step 1: Clean the surface of the power semiconductor device; Step 2: Send the power semiconductor device to the visual inspection system, adjust the light source intensity and angle, and use the camera and lens of the visual inspection system to capture images of the device; Step 3: Process and analyze the collected images to determine whether the device is qualified; Step 4: Mark or remove the devices that fail the appearance inspection, and screen the devices whose package thickness exceeds the preset value; Step 5: Use X-ray equipment to perform imaging operations on the device with excessive thickness, and use a detector to capture the X-rays passing through the device and convert them into image data; Step 6: Analyze the image data to determine whether there are defects inside the device; Step 7: Mark or remove the components that fail the X-ray inspection.
[0006] Further preferably, in step one, the surface cleaning treatment includes a purging treatment and a plasma cleaning treatment, the purging treatment of the power semiconductor device uses dry nitrogen or argon, and the plasma cleaning treatment uses a plasma cleaning machine to complete the cleaning operation.
[0007] Further preferably, in step 2, the image acquisition angle of the visual inspection system is a combination of two or more of a top-view angle, a front-view angle, a side-view angle and an oblique-view angle.
[0008] Further preferably: in step three, the image processing includes denoising and contrast enhancement, converting the image to the frequency domain using Fourier transform, suppressing high-frequency noise through a filter, and then restoring the image through inverse Fourier transform, and sharpening the image using the Laplace operator to highlight the edges and details of the image.
[0009] Further preferred: in step three, the edge information of the image is extracted using the Sobel operator, the texture features of the image are analyzed using the grayscale co-occurrence matrix, the image is classified and identified using a convolutional neural network machine learning algorithm, and the feature information is analyzed to determine whether the device has defects.
[0010] Further preferably, in step five, the detector is mounted with one of a scintillator, a photodiode array or a CMOS camera.
[0011] Further preferably, in step six, the distribution and attenuation of X-rays inside the semiconductor device are analyzed using the image data to determine whether there are defects inside the device with excessive thickness.
[0012] Further preferably: in step seven, the power semiconductor devices that are not marked or rejected are qualified products.
[0013] A power semiconductor device appearance inspection device includes a cleaning unit, an image acquisition unit, an image analysis unit, a screening unit and an X-ray unit: The cleaning unit is used for surface cleaning of power semiconductor devices; The image acquisition unit is used to acquire multi-angle images of the power semiconductor device; The image analysis unit is used to analyze multi-angle images and X-ray images of semiconductor devices and determine whether the semiconductor devices are qualified; The screening unit is used to screen qualified products, defective products and products with excessive thickness; The X-ray unit is used to emit X-rays and acquire an X-ray image of the semiconductor device.
[0014] An electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for detecting the appearance of a power semiconductor device.
[0015] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution: 1. The present invention performs appearance inspection on power semiconductor devices through a visual inspection system, and screens qualified products, defective products and products with excessive thickness according to the inspection results. There is no need for staff to manually inspect defects of semiconductor power devices, which reduces the workload of staff and improves inspection accuracy and efficiency.
[0016] 2. The present invention uses X-rays to detect defects in products with excessive thickness, thereby avoiding misjudgment or omission of internal defects in products and improving product quality.
[0017] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 is a flow chart of the present invention; Figure 2 It is a structural diagram of the device of the present invention. DETAILED DESCRIPTION
[0020] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
[0021] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.
[0022] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.
[0023] Example 1 like Figure 1 As shown, an embodiment of the present invention provides a method for detecting the appearance of a power semiconductor device, comprising the following steps: Step 1: Perform surface cleaning on the power semiconductor device. The surface cleaning includes purging and plasma cleaning. The purging of the power semiconductor device uses dry nitrogen, and the plasma cleaning uses a plasma cleaning machine to complete the cleaning operation. Step 2: Send the power semiconductor device to the visual inspection system, adjust the light source intensity and angle, and use the camera and lens of the visual inspection system to collect images of the device. The image collection angles of the visual inspection system are the top view angle and the front view angle; Step 3: Process and analyze the collected images to determine whether the device is qualified. Image processing includes denoising and contrast enhancement. The image is converted to the frequency domain using Fourier transform, and high-frequency noise is suppressed by filters. The image is then restored by inverse Fourier transform. The image is sharpened using the Laplace operator to highlight the edges and details of the image. The edge information of the image is extracted using the Sobel operator. The texture features of the image are analyzed using the gray-level co-occurrence matrix. The image is classified and identified using the convolutional neural network machine learning algorithm, and the feature information is analyzed to determine whether the device has defects. Step 4: Mark the devices that fail the appearance inspection, and screen the devices whose package thickness exceeds the preset value; Step 5: Use X-ray equipment to perform imaging operations on the device with excessive thickness, and use a detector to capture the X-rays passing through the device and convert them into image data. The detector is equipped with a photodiode array; Step 6: Analyze the image data to determine whether there are defects inside the device. Use the image data to analyze the distribution and attenuation of X-rays inside the semiconductor device to determine whether there are defects inside the device with excessive thickness. Step 7: Mark the devices that have not passed the X-ray inspection. The power semiconductor devices that have not been marked are qualified products.
[0024] Example 2 like Figure 1 As shown, an embodiment of the present invention provides a method for detecting the appearance of a power semiconductor device, comprising the following steps: Step 1: Perform surface cleaning on the power semiconductor device. The surface cleaning includes purging and plasma cleaning. The purging of the power semiconductor device uses dry argon gas, and the plasma cleaning uses a plasma cleaning machine to complete the cleaning operation. The power semiconductor device is cleaned to prevent impurities from affecting the detection. Step 2: Send the power semiconductor device to the visual inspection system, adjust the light source intensity and angle, and use the camera and lens of the visual inspection system to collect images of the device. The image collection angles of the visual inspection system are the top view angle, the side view angle, and the oblique view angle. By adjusting the light source intensity and angle, the image clarity is improved; Step 3: Process and analyze the collected images to determine whether the device is qualified. Image processing includes denoising and contrast enhancement. The image is converted to the frequency domain using Fourier transform, and high-frequency noise is suppressed by filters. The image is then restored by inverse Fourier transform. The image is sharpened using the Laplace operator to highlight the edges and details of the image. The edge information of the image is extracted using the Sobel operator. The texture features of the image are analyzed using the gray-level co-occurrence matrix. The image is classified and identified using the convolutional neural network machine learning algorithm, and the feature information is analyzed to determine whether the device has defects. Step 4: Remove the devices that fail the appearance inspection and screen the devices whose package thickness exceeds the preset value. The removal and screening operations are completed with the assistance of a robot. Step 5: Use X-ray equipment to perform imaging operations on the device with excessive thickness, capture the X-rays passing through the device through a detector and convert them into image data. The detector is equipped with a CMOS camera, which is used to obtain the image; Step 6: Analyze the image data to determine whether there are defects inside the device. Use the image data to analyze the distribution and attenuation of X-rays inside the semiconductor device to determine whether there are defects inside the device with excessive thickness. When the distribution and attenuation of X-rays inside the semiconductor device are abnormal, it is determined that there are defects inside the device with excessive thickness. Step 7: Eliminate the devices that fail the X-ray inspection. The power semiconductor devices that have not been eliminated are qualified products.
[0025] The present invention performs appearance inspection on power semiconductor devices through a visual inspection system, and screens qualified products, defective products and products with excessive thickness according to the inspection results. There is no need for staff to manually inspect defects of semiconductor power devices, which reduces the workload of staff and improves inspection accuracy and efficiency.
[0026] The present invention uses X-rays to perform defect detection on products with excessive thickness, thereby avoiding misjudgment or missed judgment of internal defects of products and improving product quality.
[0027] Example 3 like Figure 2 As shown, a power semiconductor device appearance inspection device includes a cleaning unit, an image acquisition unit, an image analysis unit, a screening unit and an X-ray unit: The cleaning unit is used for surface cleaning of power semiconductor devices; The image acquisition unit is used to acquire multi-angle images of the power semiconductor device; The image analysis unit is used to analyze multi-angle images and X-ray images of semiconductor devices and determine whether the semiconductor devices are qualified; The screening unit is used to screen qualified products, defective products and products with excessive thickness; The X-ray unit is used to emit X-rays and acquire an X-ray image of the semiconductor device.
[0028] An electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for detecting the appearance of a power semiconductor device.
[0029] An electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.
[0030] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as magnetic tapes and hard disks; and communication devices. The communication device can allow the electronic device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data.
[0031] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.
[0032] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for detecting the appearance of a power semiconductor device, characterized in that: The following steps are involved: Step 1: Clean the surface of the power semiconductor device; Step 2: Send the power semiconductor device to the visual inspection system, adjust the light source intensity and angle, and use the camera and lens of the visual inspection system to capture images of the device; Step 3: Process and analyze the collected images to determine whether the device is qualified; Step 4: Mark or remove the devices that fail the appearance inspection, and screen the devices whose package thickness exceeds the preset value; Step 5: Use X-ray equipment to perform imaging operations on the device with excessive thickness, and use a detector to capture the X-rays passing through the device and convert them into image data; Step 6: Analyze the image data to determine whether there are defects inside the device; Step 7: Mark or remove the components that fail the X-ray inspection.
2. A method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step one, the surface cleaning process includes a purging process and a plasma cleaning process. The purging process of the power semiconductor device uses dry nitrogen or argon gas, and the plasma cleaning process uses a plasma cleaning machine to complete the cleaning operation.
3. A method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step 2, the image acquisition angle of the visual inspection system is a combination of two or more of a top-view angle, a front-view angle, a side-view angle and an oblique-view angle.
4. A method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step three, image processing includes denoising and contrast enhancement. The image is converted to the frequency domain using Fourier transform, high-frequency noise is suppressed by filters, and then the image is restored by inverse Fourier transform. The image is sharpened using the Laplace operator to highlight the edges and details of the image.
5. The method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step three, the Sobel operator is used to extract the edge information of the image, the gray-level co-occurrence matrix is used to analyze the texture features of the image, the convolutional neural network machine learning algorithm is used to classify and identify the image, and the feature information is analyzed to determine whether the device has defects.
6. A method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step five, the detector is mounted with one of a scintillator, a photodiode array or a CMOS camera.
7. A method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step six, the image data is used to analyze the distribution and attenuation of X-rays inside the semiconductor device to determine whether there are defects inside the device with excessive thickness.
8. The method for detecting the appearance of a power semiconductor device according to claim 1, characterized in that: In step seven, the power semiconductor devices that are not marked or rejected are qualified products.
9. A power semiconductor device appearance inspection device, applied to a power semiconductor device appearance inspection method according to any one of claims 1 to 8, characterized in that: Including cleaning unit, image acquisition unit, image analysis unit, screening unit and X-ray unit: The cleaning unit is used for surface cleaning of power semiconductor devices; The image acquisition unit is used to acquire multi-angle images of the power semiconductor device; The image analysis unit is used to analyze multi-angle images and X-ray images of semiconductor devices and determine whether the semiconductor devices are qualified; The screening unit is used to screen qualified products, defective products and products with excessive thickness; The X-ray unit is used to emit X-rays and acquire an X-ray image of the semiconductor device.
10. An electronic device, characterized in that: The electronic device comprises: at least one processor, and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for appearance inspection of a power semiconductor device as described in any one of claims 1-8.