主成分分析及聚类方法在碲镉汞晶片参数判别中的应用研究OA北大核心CSTPCD
Application of principal component analysis and clustering methods in the discrimination of parameters in HgCdTe crystals
基于主成分分析和聚类方法提出了一种碲镉汞晶片参数筛选方法,建立了对碲镉汞晶片参数进行筛选的数据模型,模型中通过对初始晶片数据进行清洗和分析,利用主成分分析(PCA)降维法和基于密度的聚类算法(DBSCAN),确定了晶片数据中最密集的区域.同时利用流片后得到高性能芯片的优质碲镉汞晶片参数拟合边界椭圆曲线,并将其作为优质晶片的判断标准,能够根据输入的晶片电学和光学参数生成晶片评级,得到了大于90%的覆盖率.
A method for selecting parameters in HgCdTe crystals has been proposed,utilizing Principal Component Analysis(PCA)and clustering methods,with the establishment of a data model for screening the parameters of HgCdTe crystals.Within the model,the initial crystal data undergoes a cleaning and analysis process.PCA is employed for dimensionality reduction,and the Density-Based Spatial Clustering of Applications with Noise(DBSCAN)algo-rithm is used to identify the densest regions within the crystal data.Furthermore,the high-performance chip data,ob-tained after post-processing,is utilized to fit boundary ellipses for high-quality HgCdTe crystal parameters.These ellips-es act as criteria for identifying high-quality crystals.The model is capable of generating crystal ratings based on input electrical and optical parameters with a coverage rate exceeding 90%.
吴佳昊;乔辉;李向阳
中国科学院上海技术物理研究所,上海 200083||上海科技大学 信息科学与技术学院,上海 201210中国科学院上海技术物理研究所,上海 200083
物理学
碲镉汞晶片筛选主成分分析聚类
HgCdTecrystal parameter selectionprincipal component analysisclustering analysis
《红外与毫米波学报》 2024 (004)
490-496 / 7
国家自然科学基金重点项目(42330110) Supported by the State Key Program of National Natural Science of China(42330110)
评论