Submicron wafer manufacturing process defect visual verification experiment platform
By building a visual verification experimental platform for defects in submicron-scale crystal cell manufacturing process, combined with deep learning algorithms, automated and intelligent defect detection is realized, solving the problems of low efficiency and susceptibility to human factors in the existing technology, improving the accuracy and efficiency of detection, and supporting the development of the semiconductor industry.
Patent Information
- Application Number
- CN202510501694.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-21
- Publication Date
- 2025-08-01
AI Technical Summary
In the prior art, visual detection of defects in submicron-scale crystal cell manufacturing process mainly relies on artificial microscope observation, which is inefficient and susceptible to human factors, resulting in the accuracy and reliability of the detection results being unable to be guaranteed.
The visual verification experimental platform for defects in submicron-level crystal cell manufacturing process is adopted, including optical microscopes, image acquisition devices, image processing devices, defect identification devices, data analysis devices, control devices, user interfaces, data storage devices, robotic arm devices, high-precision positioning systems and light source systems, and combined with deep learning algorithms, automated and intelligent defect detection is achieved.
It realizes rapid and accurate detection of submicron-scale crystal cell manufacturing process defects, improves detection efficiency and accuracy, reduces the influence of human factors, and provides strong support for the development of the semiconductor industry.
Smart Images
Figure CN120404737A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of visual inspection of semiconductor process defects, and particularly to a visual verification experimental platform for sub-micron chip manufacturing process defects. Background Art
[0002] A semiconductor is a substance with electrical conductivity between that of an insulator and a conductor. Its electrical conductivity is easily controlled and it can be used as a component material for information processing. From the perspective of technological or economic development, semiconductors are very important. The core units of many electronic products, such as computers, mobile phones, and digital recorders, utilize the change in the electrical conductivity of semiconductors to process information. Common semiconductor materials include silicon, germanium, gallium arsenide, etc. Among various semiconductor materials, silicon is the most influential one in commercial applications. A material with electrical conductivity between that of a conductor and an insulator at room temperature is called a semiconductor. We usually refer to materials with poor electrical conductivity and heat conduction, such as diamond, artificial crystals, amber, ceramics, etc., as insulators, and metals with good electrical and heat conduction, such as gold, silver, copper, iron, tin, aluminum, etc., as conductors. We can simply refer to the material between a conductor and an insulator as a semiconductor. Compared with conductors and insulators, the discovery of semiconductor materials was the latest. It wasn't until the 1930s, after the improvement of material purification technology, that the existence of semiconductors was truly recognized by the academic community. The classification of semiconductors can be divided into: integrated circuit devices, discrete devices, optoelectronic semiconductors, logic ICs, analog ICs, memories, etc. in terms of manufacturing technology. Generally, these are further divided into smaller categories. In addition, there are classifications based on application fields, design methods, etc. Although not commonly used, there is also a classification method according to IC, LSI, VLSI (ultra-large LSI) and their scales. In addition, there is a classification method according to the signals they process, which can be divided into analog, digital, analog-digital hybrid, and functional classifications. There are many semiconductor materials, which can be divided into elemental semiconductors and compound semiconductors according to chemical composition. Germanium and silicon are commonly used elemental semiconductors; compound semiconductors include group III-V compounds (such as gallium arsenide, gallium phosphide, etc.), group II-VI compounds (such as cadmium sulfide, zinc sulfide, etc.), oxides (such as oxides of manganese, chromium, iron, copper), and solid solutions composed of group III-V compounds and group II-VI compounds (such as gallium aluminum arsenide, gallium arsenide phosphide, etc.). In addition to the above crystalline semiconductors, there are also amorphous glass semiconductors, organic semiconductors, etc. The semiconductor industry belongs to the electronic information industry and is a hardware industry, which is the foundation of the information age and an industry developed based on semiconductors. With the rapid development of the semiconductor industry, sub-micron chip manufacturing processes play an increasingly important role in integrated circuit manufacturing. However, due to the complexity and fineness of sub-micron chip manufacturing processes, various process defects are extremely likely to occur during the manufacturing process, such as particles, scratches, contamination, etc. These defects will seriously affect the performance and reliability of the chips.
[0003] Currently, the traditional visual inspection method for defects in sub-micron chip manufacturing processes mainly relies on manual microscope observation and manual judgment. This method is not only inefficient but also easily affected by human factors, resulting in the inability to guarantee the accuracy and reliability of the inspection results.
[0004] Therefore, we propose a visual verification experimental platform for defects in sub-micron chip manufacturing processes. Summary of the Invention
[0005] The present invention mainly solves the technical problems existing in the above-mentioned prior art and provides a visual verification experimental platform for defects in sub-micron chip manufacturing processes.
[0006] To achieve the above object, the present invention adopts the following technical solutions. A visual verification experimental platform for defects in sub-micron chip manufacturing processes includes an optical microscope, an image acquisition device, an image processing device, a defect recognition device, a data analysis device, a control device, a user interface, a data storage device, a robotic arm device, a high-precision positioning system, and a light source system. The optical microscope is used to provide a high-magnification observation field of view, enabling the details of sub-micron chips to be clearly presented. The image acquisition device is responsible for capturing the chip image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs denoising and enhancement preprocessing on the captured image to improve the accuracy of subsequent defect recognition.
[0007] Preferably, the defect recognition device adopts a deep learning algorithm and can automatically identify particle, scratch, and contamination process defects in the image.
[0008] Preferably, the data analysis device performs statistical analysis on the identified defects, such as the number, size, and distribution of defects, to provide a basis for process improvement.
[0009] Preferably, the control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device.
[0010] Preferably, the user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the inspection results.
[0011] Preferably, the data storage device is used to store experimental data and inspection results for convenient subsequent data analysis and processing.
[0012] Preferably, the robotic arm device is used for automatic loading and unloading to improve the automation level of the experiment.
[0013] Preferably, the high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment.
[0014] Preferably, the light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition.
[0015] Beneficial effects
[0016] The present invention provides a visual verification experimental platform for defects in sub-micron chip manufacturing processes, having the following
[0017] Beneficial effects:
[0018] (1) The visual verification experimental platform for defects in sub-micron chip manufacturing processes of the present invention realizes rapid and accurate detection and verification of defects in sub-micron chip manufacturing processes, improves detection efficiency and accuracy, reduces the influence of human factors, and provides strong support for the development of the semiconductor industry.
[0019] (2) The visual verification experimental platform for defects in sub-micron chip manufacturing processes, by setting up a defect recognition device and applying deep learning algorithms, enables the defect recognition device to automatically identify particle, scratch, and contamination process defects in images, greatly improving the accuracy and efficiency of defect recognition, reducing the need for manual intervention, and reducing the possibility of human error.
[0020] (3) The visual verification experimental platform for defects in sub-micron chip manufacturing processes, by setting up a data analysis device, statistically analyzes the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement, helping to optimize the manufacturing process, and improving product quality and production efficiency.
[0021] (4) The visual verification experimental platform for defects in sub-micron chip manufacturing processes, by setting up a control device, user interface, and data storage device, realizes the automated and intelligent operation of the platform, improves the automation level and operation convenience of the experiment, and reduces the experimental cost and time cost.
[0022] (5) The visual verification experimental platform for defects in sub-micron chip manufacturing processes, by setting up a high-precision positioning system and a light source system, and applying the high-precision positioning system and the light source system, ensures the precise positioning of the robotic arm device and the optical microscope and the stability of the illumination environment, providing strong guarantee for the accuracy and reliability of the experimental results. Description of the drawings
[0023] Figure 1 It is a system module diagram of the present invention. Specific implementation manners
[0024] Example 1: A visual verification experimental platform for defects in sub-micron chip manufacturing processes, such asFigure 1 As shown, it includes an optical microscope, an image acquisition device, an image processing device, a defect recognition device, a data analysis device, a control device, a user interface, a data storage device, a robotic arm device, a high-precision positioning system, and a light source system. The optical microscope is used to provide a high-magnification observation field of view, enabling the details of sub-micron-level wafers to be clearly presented. The image acquisition device is responsible for capturing the wafer image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs preprocessing such as denoising and enhancement on the captured image to improve the accuracy of subsequent defect recognition. The defect recognition device uses deep learning algorithms to automatically identify particles, scratches, and contamination process defects in the image. The data analysis device statistically analyzes the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results. The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading, improving the automation level of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment. The light source system provides a stable and uniform lighting environment, providing good lighting conditions for image acquisition and defect recognition. The visual verification experimental platform for sub-micron-level wafer manufacturing process defects of the present invention realizes the rapid and accurate detection and verification of sub-micron-level wafer manufacturing process defects, improves the detection efficiency and accuracy, reduces the influence of human factors, and provides strong support for the development of the semiconductor industry.
[0025] Example 2: On the basis of Example 1, as Figure 1As shown, an optical microscope is used to provide a high-magnification observation field of view, enabling the details of sub-micron-level wafers to be clearly presented. The image acquisition device is responsible for capturing the wafer image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs preprocessing such as denoising and enhancement on the captured image to improve the accuracy of subsequent defect recognition. The defect recognition device uses deep learning algorithms and can automatically identify particle, scratch, and contamination process defects in the image. The data analysis device conducts statistical analysis on the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform, view the detection results. The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading, improving the automation level of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment. The light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition. By setting up the defect recognition device and applying deep learning algorithms, the defect recognition device can automatically identify particle, scratch, and contamination process defects in the image, greatly improving the accuracy and efficiency of defect recognition, reducing the need for manual intervention, and reducing the possibility of human error.
[0026] Embodiment 3: On the basis of Embodiment 1 and Embodiment 2, as Figure 1As shown, the image acquisition device is responsible for acquiring the wafer image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs denoising and enhancement preprocessing on the acquired image to improve the accuracy of subsequent defect recognition. The defect recognition device uses deep learning algorithms to automatically identify particles, scratches, and contamination process defects in the image. The data analysis device performs statistical analysis on the identified defects, such as the number, size, and distribution of defects, to provide a basis for process improvement. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results. The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading to improve the automation of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment. The light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition. By setting up the data analysis device, statistical analysis is performed on the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement, helping to optimize the manufacturing process, and improving product quality and production efficiency.
[0027] Embodiment 4: On the basis of Embodiment 1, Embodiment 2, and Embodiment 3, as Figure 1 shown, the image processing device performs denoising and enhancement preprocessing on the acquired image to improve the accuracy of subsequent defect recognition. The defect recognition device uses deep learning algorithms to automatically identify particles, scratches, and contamination process defects in the image. The data analysis device performs statistical analysis on the identified defects, such as the number, size, and distribution of defects, to provide a basis for process improvement. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results. The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading to improve the automation of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment. The light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition. By setting up the control device, user interface, and data storage device, the automatic and intelligent operation of the platform is achieved, improving the automation degree and operation convenience of the experiment, and reducing the experimental cost and time cost.
[0028] Embodiment 5: On the basis of Embodiment 1, Embodiment 2, Embodiment 3, and Embodiment 4, as Figure 1As shown, the defect recognition device uses deep learning algorithms and can automatically identify particle, scratch, and contamination process defects in images. The data analysis device conducts statistical analysis on the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results. The data storage device is used to store experimental data and detection results, facilitating subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading, improving the automation level of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, guaranteeing the accuracy of the experiment. The light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition. By setting up the high-precision positioning system and the light source system, through the application of the high-precision positioning system and the light source system, the precise positioning of the robotic arm device and the optical microscope and the stability of the illumination environment are ensured, providing a strong guarantee for the accuracy and reliability of the experimental results.
[0029] Working principle of the present invention: By setting multiple components including an optical microscope, an image acquisition device, an image processing device, a defect recognition device, a data analysis device, a control device, a user interface, a data storage device, a robotic arm device, a high-precision positioning system, and a light source system, an automated and intelligent operation of a wafer surface defect detection platform based on deep learning is achieved. The optical microscope is used to provide a high-magnification observation field of view, enabling the details of sub-micron wafers to be clearly presented. The image acquisition device is responsible for capturing the wafer image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs denoising and enhancement preprocessing on the captured image to improve the accuracy of subsequent defect recognition. The defect recognition device uses deep learning algorithms to automatically identify particles, scratches, and contamination process defects in the image, greatly improving the accuracy and efficiency of defect recognition, reducing the need for manual intervention, and lowering the possibility of human error. The data analysis device performs statistical analysis on the identified defects, such as the number, size, and distribution of defects, providing a basis for process improvement, helping to optimize the manufacturing process, and improving product quality and production efficiency. The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device, ensuring the accuracy and automation of the experiment. The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results. The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing. The robotic arm device is used for automatic loading and unloading, improving the automation of the experiment. The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment. The light source system provides a stable and uniform illumination environment, providing good lighting conditions for image acquisition and defect recognition. Through the coordinated action of each component, the present invention realizes an efficient, accurate, and automated wafer surface defect detection platform, providing strong support for quality control and process improvement in the wafer manufacturing process.
[0030] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.
Claims
1. A visual verification experimental platform for sub-micron chip manufacturing process defects, characterized in that, It includes an optical microscope, an image acquisition device, an image processing device, a defect recognition device, a data analysis device, a control device, a user interface, a data storage device, a robotic arm device, a high-precision positioning system, and a light source system. The optical microscope is used to provide a high-magnification observation field of view, enabling the details of sub-micron wafers to be clearly presented. The image acquisition device is responsible for capturing the wafer image under the microscope and converting it into a digital signal for subsequent processing. The image processing device performs denoising and enhancement preprocessing on the captured image to improve the accuracy of subsequent defect recognition.
2. The visual verification experimental platform for the defects of sub-micron chip manufacturing process according to claim 1, characterized in that: The defect recognition device uses deep learning algorithms and can automatically identify particle, scratch, and contamination process defects in the image.
3. The visual verification experimental platform for sub-micron chip manufacturing process defects according to claim 1, wherein: The data analysis device performs statistical analysis on the identified defects, such as the number, size, and distribution of defects, to provide a basis for process improvement.
4. The visual verification experimental platform for the defects of sub-micron chip manufacturing process according to claim 1, characterized in that: The control device is responsible for the operation control of the entire platform, including the focal length adjustment of the optical microscope and the motion control of the robotic arm device.
5. The visual verification experimental platform for the defects of sub-micron chip manufacturing process according to claim 1, characterized in that: The user interface provides a friendly operation interface, enabling users to conveniently control the operation of the platform and view the detection results.
6. The visual verification experimental platform for the manufacturing process defects of sub-micron chips according to claim 1, wherein: The data storage device is used to store experimental data and detection results for convenient subsequent data analysis and processing.
7. The visual verification experimental platform for the defects of sub-micron chip manufacturing process according to claim 1, wherein: The robotic arm device is used for automatic loading and unloading to improve the automation level of the experiment.
8. The visual verification experimental platform for sub-micron chip manufacturing process defects according to claim 1, characterized in that: The high-precision positioning system ensures the precise positioning of the robotic arm device and the optical microscope, ensuring the accuracy of the experiment.
9. The visual verification experimental platform for sub-micron chip manufacturing process defects according to claim 1, wherein: The light source system provides a stable and uniform lighting environment, providing good lighting conditions for image acquisition and defect recognition.