17959793. AUTOMATED MAPPING METHOD OF CRYSTALLINE STRUCTURE AND ORIENTATION OF POLYCRYSTALLINE MATERIAL WITH DEEP LEARNING simplified abstract (Samsung Electronics Co., Ltd.)
AUTOMATED MAPPING METHOD OF CRYSTALLINE STRUCTURE AND ORIENTATION OF POLYCRYSTALLINE MATERIAL WITH DEEP LEARNING
Organization Name
Inventor(s)
Young-Min Kim of Seongnam-si (KR)
Young-Hoon Kim of Suwon-si (KR)
AUTOMATED MAPPING METHOD OF CRYSTALLINE STRUCTURE AND ORIENTATION OF POLYCRYSTALLINE MATERIAL WITH DEEP LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17959793 titled 'AUTOMATED MAPPING METHOD OF CRYSTALLINE STRUCTURE AND ORIENTATION OF POLYCRYSTALLINE MATERIAL WITH DEEP LEARNING
Simplified Explanation
The patent application describes a method for mapping the crystal information of a polycrystalline material using electron beam diffraction patterns and deep convolutional neural networks. Here are the key points:
- The method involves scanning an electron beam over the polycrystalline material and acquiring a diffraction pattern.
- A clustering algorithm is then applied to the diffraction pattern to generate multiple clusters.
- Each cluster is analyzed using a deep convolutional neural network algorithm to extract crystal information.
- The crystal information is then used to generate a two-dimensional image that maps the acquired data.
Potential applications of this technology:
- Material science research: This method can be used to study the crystal structure and properties of various polycrystalline materials, aiding in the development of new materials with desired characteristics.
- Quality control in manufacturing: The method can be employed to analyze the crystal information of polycrystalline materials used in manufacturing processes, ensuring the quality and consistency of the materials.
- Semiconductor industry: The technology can be applied to analyze the crystal structure of semiconductor materials, helping in the development and optimization of electronic devices.
Problems solved by this technology:
- Traditional methods for analyzing crystal information in polycrystalline materials are time-consuming and require manual interpretation. This method automates the process and provides a more efficient and accurate analysis.
- The use of deep convolutional neural networks allows for the extraction of crystal information from diffraction patterns, which can be complex and difficult to interpret using conventional techniques.
Benefits of this technology:
- Improved efficiency: The automated analysis of diffraction patterns and extraction of crystal information speeds up the process compared to manual methods.
- Enhanced accuracy: The use of deep convolutional neural networks improves the accuracy of crystal information extraction, reducing the potential for human error.
- Non-destructive analysis: The method utilizes electron beam diffraction, which is a non-destructive technique, allowing for the analysis of materials without damaging them.
Original Abstract Submitted
A method for two-dimensional mapping of crystal information of a polycrystalline material may include acquiring a diffraction pattern acquired by scanning an electron beam to a polycrystalline material, generating a plurality of clusters by applying a clustering algorithm to the acquired diffraction pattern based on unsupervised learning, acquiring crystal information of the polycrystalline material by applying a parallel deep convolutional neural network (DCNN) algorithm to each of the plurality of generated clusters based on supervised learning, and generating a two-dimensional image in which the acquired crystal information is mapped.
