特征提取及数据扩充的GA-LightGBM半导体质量检测方法
GA-LightGBM method of semiconductor quality inspection based on feature extraction and data expansion
程云飞 1周丽芳 1赵波 1谭佳伟 1王淑影1
作者信息
- 1. 长春工业大学 数学与统计学院,长春 130012
- 折叠
摘要
半导体质量检测数据具有的"相关性、冗余性、不平衡性"等特点,导致传统的分类算法效率较低,为此,提出一种基于特征提取及数据扩充的GA-LightGBM(genetic algorithm-light gradient boosting machine)质量检测方法.通过结合主成分分析(principal component analysis,PCA)、合成少数类过采样技术(synthetic minority oversampling technique,SMOTE)、遗传算法和LightGBM这 4 种方法,实现对产品质量的有效识别.实验结果表明,相较于传统分类算法,提出的方法可以有效提升质量检测的效率.
Abstract
Semiconductor quality inspection data exhibit characteristics such as correlation,redundancy,and imbalance,which lead to lower efficiency in traditional classification algorithms.To address this challenge,we propose a quality inspec-tion method named GA-LightGBM(genetic algorithm-light gradient boosting machine)that leverages feature extraction and data augmentation techniques.This approach combines principal component analysis(PCA),synthetic minority oversam-pling technique(SMOTE),genetic algorithm,and LightGBM.Experimental results demonstrate that,compared to tradi-tional classification algorithms,the proposed method significantly improves the efficiency of quality inspection.
关键词
质量检测/主成分分析/合成少数类过采样技术/GA-LightGBMKey words
quality inspection/principal component analysis/synthetic minority oversampling technique/genetic algorithm-light gradient boosting machine引用本文复制引用
基金项目
吉林省重大科技专项(20210301038GX)
吉林省重大科技专项(20220301031GX)
吉林省科技厅重点研发项目(20230204078YY)
出版年
2024
国家科技期刊平台
NSTL
万方数据