Wafer yield prediction method based on improved continuous deep belief network

被引：0
|
作者：
Xu H. [1 ]
Zhang J. [1 ]
Lyu Y. [1 ]
Zheng P. [2 ]
机构：
[1] Institute of Intelligent Manufacturing, College of Mechanical Engineering, Donghua University, Shanghai
[2] Institute of Intelligent Manufacturing and Information Engineering, School of Mechanical and Power Engineering, Shanghai Jiao Tong University, Shanghai
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2020年 / 26卷 / 09期
基金：
中国国家自然科学基金;
关键词：
Continuous deep belief network; Principal component analysis; Wafer acceptance test parameters; Wafer yield prediction;
D O I：
10.13196/j.cims.2020.09.008
中图分类号：
学科分类号：
摘要：
Wafer yield is a key indicator for measuring the quality of semiconductor products. Stable and accurate predictions can help identify defects in wafer processing, improve chip quality and control chip production costs. Due to the influence factors of wafer yield, large data volume and complex data relationship, based on the electrical test parameters in wafer processing, a wafer yield prediction method based on improved continuous deep belief network was proposed. A two-stage data preprocessing method for wafer electrical test parameters was proposed, in which the first stage performed data cleaning on missing values and outliers in the wafer electrical test parameters, and the principal component analysis was performed on the multi-collinearity relationship between wafer electrical test parameters to obtain the input variables of predictive model in the second stage. A wafer yield prediction model was designed based on deep belief network, which realized the automatic extraction of key features by improving the continuous-type restricted Boltzmann machine of the hidden layer, and the error back propagation mechanism of the output layer was used to accurately predict the wafer yield. With the laboratory actual production data, the prediction accuracy of the proposed method and the existing literature method was compared, and the effectiveness of the method was verified. © 2020, Editorial Department of CIMS. All right reserved.
引用
收藏
页码：2388 / 2395
页数：7
相关论文
共 17 条
  • [1] SUN Hong, Defect mode of copper interconnection process and its effect on the yield of integrated circuits, (2009)
  • [2] RAGHAVACHARI M, SRINIVASAN A, SULLO P., Poisson mixture yield models for integrated circuits: A critical review, Microelectronics Reliability, 37, 4, pp. 565-580, (1997)
  • [3] XU Wenhui, Development of an interval neural network for the recognition of semiconductor wafer defects and the prediction of wafer yield, (1998)
  • [4] LIU Tingyi, GRNN's construction and analysis of yield pattern in wafer fabrication, master's thesis of Institute of industrial engineering, (1999)
  • [5] LIN Ruishan, Using artifical neural network for wafer test yield prediction, (2004)
  • [6] ZHANG Bingyu, CHEN Kuntai, WANG Zhenyu, Using WAT data to construct the prediction model of wafer yield, Journal of Quality, 18, 6, pp. 519-537, (2011)
  • [7] KANG Sheng, Application of multivariate piecewise model based on principal component analysis to predict wafer yield in IC, (2015)
  • [8] QIU Minghui, CAO Zhengcai, LIU Min, Et al., Prediction method of yield of semiconductor production line based on DBSCAN and FSVM, Computer Integrated Manufacturing Systems, 22, 11, pp. 2594-2601, (2016)
  • [9] GIACALONE M, PANARELLO D, MATTERA R., Multicollinearity in regression:An efficiency comparison between L p-norm and least squares estimators, Quality & Quantity, 52, 4, pp. 1831-1859, (2018)
  • [10] LIU Yumin, ZHANG Shuai, Dynamic process quality abnormality monitoring model based on multi-principal component features and support vector machines, Computer Integrated Manufacturing Systems, 24, 3, pp. 703-710, (2018)
12