大数据驱动的晶圆工期预测关键参数识别方法

doi:10.3901/JME.2018.23.185

机械工程学报 ›› 2018, Vol. 54 ›› Issue (23): 185-191.doi: 10.3901/JME.2018.23.185

大数据驱动的晶圆工期预测关键参数识别方法

汪俊亮^1,2, 张洁¹

1. 东华大学机械工程学院上海 201620;
2. 上海交通大学机械与动力工程学院上海 200240

收稿日期:2017-12-05 修回日期:2018-03-05 出版日期:2018-12-05 发布日期:2018-12-05
通讯作者: 张洁(通信作者),男,1963年出生,博士,教授,博士研究生导师。主要研究方向为智能制造系统、工业大数据。E-mail:mezhangjie@dhu.edu.cn
作者简介:汪俊亮,男,1991年出生,博士,讲师。主要研究方向为大数据驱动的智能制造系统运行与优化。E-mail:wjlwhut@163.com
基金资助:
国家自然科学基金（51435009）和上海市经信委（201602018）资助项目。

Big Data Driven Key Factor Identification for Cycle-time Forecasting of Wafer Lots in Semiconductor Wafer Fabrication System

WANG Junliang^1,2, ZHANG Jie¹

1. College of Mechanical Engineering, Donghua University, Shanghai 201620;
2. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240

Received:2017-12-05 Revised:2018-03-05 Online:2018-12-05 Published:2018-12-05

摘要/Abstract

摘要： 工期是晶圆制造中的重要性能指标，对其进行精准预测可促进系统运行优化，保证订单的准时交付率。针对晶圆工期影响参数多、数据体量大且作用机理复杂的特点，提出数据驱动的晶圆工期关键参数过滤方法，识别影响晶圆工期波动的关键参数。分析晶圆工期潜在影响参数，构建候选参数集；基于信息熵方法设计关键参数的入选测度，综合度量参数间的相关性、冗余性与互补性；提出过滤式的关键参数识别算法，滤取影响工期波动的关键参数子集。采用实例数据，从1 202个候选参数中过滤得到78个关键参数，并采用神经网络模型进行工期预测，结果表明，该方法在预测精度和稳定性上都优于采用全局参数的多元线性回归与神经网络方法。

关键词: 参数筛选, 大数据, 工期预测, 晶圆制造

Abstract: The semiconductor wafer fabrication system (SWFS) should make changes on the product mix and manufacturing process control frequently to meet customers' fluctuating demands, and the cycle time (CT) forecasting is crucial in the promise of a good delivery-time. A data driven method is proposed to select key factors by estimating the correlation between candidate factors and wafer lots' CT. Firstly, all candidate factors are collected for correlation analysis. Subsequently, a mutual information based method is designed to determine key factors as the input of the forecasting model. Eventually, 78 CT-related factors stood out from 1 202 candidates and replaced 5 global factors (used as reference) to predict CTs of wafer lots. To evaluate the performance, a back propagation network is designed to forecast the CT of wafer lots by using the selected key factors. The results indicate that the proposed approach had higher accuracy than linear regression and FCM-BPN in CT forecasting in large scale dataset.

Key words: big data, cycle-time forecasting, factor selection, Wafer manufacturing

中图分类号:

TG156

汪俊亮, 张洁. 大数据驱动的晶圆工期预测关键参数识别方法[J]. 机械工程学报, 2018, 54(23): 185-191.

WANG Junliang, ZHANG Jie. Big Data Driven Key Factor Identification for Cycle-time Forecasting of Wafer Lots in Semiconductor Wafer Fabrication System[J]. Journal of Mechanical Engineering, 2018, 54(23): 185-191.

参考文献

[1] PAN Cong,ZHANG Jie,QIN Wei. Real-time OHT dispatching mechanism for the interbay automated material handling system with shortcuts and by passes[J]. Chinese Journal of Mechanical Engineering,2017,30(3):663-675.
[2] 贾文友,江志斌,李友. 面向产品族优化时间窗下可重入批处理机调度[J]. 机械工程学报,2015,51(12):192-201. JIA Wenyou,JIANG Zhibin,LI You. Family-oriented to optimize scheduling problem of re-entrant batch processing machine with due window[J]. Journal of Mechanical Engineering,2015,51(12):192-201.
[3] LEE J H,KIM H J. Makespan analysis of Lot switching period in cluster tools[J]. IEEE Transactions on Semiconductor Manufacturing,2016,29(2):127-136.
[4] CHEN T,WANG Y. An iterative procedure for optimizing the performance of the fuzzy-neural job cycle time estimation approach in a wafer fabrication factory[J]. Mathematical Problems in Engineering,2013,2013.
[5] CHIEN C,HSU C,HSIAO C. Manufacturing intelligence to forecast and reduce semiconductor cycle time[J]. Journal of Intelligent Manufacturing,2012,23(6):2281-2294.
[6] POURVAZIRI H,PIERREVAL H. Dynamic facility layout problem based on open queuing network theory[J]. European Journal of Operational Research,2017,259(2):538-553.
[7] YU C,CHIEN C,KUO C. Exploit the value of production data to discover opportunities for saving power consumption of production tools[J]. IEEE Transactions on Semiconductor Manufacturing,2017,30(4):345-350.
[8] 张洁,高亮,秦威,等. 大数据驱动的智能车间运行分析与决策方法体系[J]. 计算机集成制造系统,2016,22(5):1220-1228. ZHANG Jie,GAO Liang,QIN Wei,et al. Big-data-driven operational analysis and decision-making methodology in intelligent workshop[J]. Computer Integrated Manufacturing Systems,2016,22(5):1220-1228.
[9] 杨俊刚,张洁,秦威,等. 面向半导体制造的大数据分析平台[J]. 计算机集成制造系统,2016,22(12):2900-2910. YANG Jungang,ZHANG Jie,QIN Wei,et al. Big data analysis platform for semiconductor manufacturing[J]. Computer Integrated Manufacturing Systems,2016,22(12):2900-2910.
[10] WANG J,ZHANG J,WANG X. A data driven cycle time prediction with feature selection in a semiconductor wafer fabrication system[J]. IEEE Transactions on Semiconductor Manufacturing,2018,31(1):173-182.
[11] SHA D Y,STORCH R L,LIU C H. Development of a regression-based method with case-based tuning to solve the due date assignment problem[J]. International Journal of Production Research,2007,45(1):65-82.
[12] ROSSI F,LENDASSE A,FRANÇOIS D,et al. Mutual information for the selection of relevant variables in spectrometric nonlinear modelling[J]. Chemometrics and Intelligent Laboratory Systems,2006,80(2):215-226.
[13] LEWIS D D. Feature selection and feature extraction for text categorization[C]//Proceedings of the workshop on Speech and Natural Language. February 23-26,1992,Harriman,New York,Association for Computational Linguistics:212-217.
[14] VERGARA J R,ESTÉVEZ P A. A review of feature selection methods based on mutual information[J]. Neural Computing and Applications,2014,24(1):175-186.
[15] PENG H,LONG F,DING C. Feature selection based on mutual information:Criteria of max-dependency,max-relevance,and min-redundancy[J]. IEEE Computer Society,2005:1226.
[16] MEYER P E,BONTEMPI G. On the use of variable complementarity for feature selection in cancer classification[J]. Workshops on Applications of Evolutionary Computa,2006,17(5):91-102.
[17] CACHON G P,TERWIESCH C. Matching supply with demand[M]. Berlin Heidelberg:Springer-Verlag,2006.
[18] HOPP W. Factory physics[M]. Long Grove:Waveland Press,2011.
[19] CHERFI A,NOUIRA K,FERCHICHI A. Very fast C4.5 decision tree algorithm[J]. Applied Artificial Intelligence,2018(3):1-19.
[20] CHEN T,WANG Y. Incorporating the FCM-BPN approach with nonlinear programming for internal due date assignment in a wafer fabrication plant[J]. Robotics and Computer-Integrated Manufacturing,2010,26(1):83-91.

大数据驱动的晶圆工期预测关键参数识别方法

Big Data Driven Key Factor Identification for Cycle-time Forecasting of Wafer Lots in Semiconductor Wafer Fabrication System

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	李川, 张绍辉, José Valente de Oliveira. 基于次优网络深度学习的3D打印机故障诊断[J]. 机械工程学报, 2019, 55(7): 73-80.
[2]	雷亚国, 贾峰, 孔德同, 林京, 邢赛博. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
[3]	王少杰, 侯亮, 方奕凯, 林浩菁, 郭涛, 焦建新. 考虑产品运行大数据的装载机变速箱优化设计[J]. 机械工程学报, 2018, 54(22): 218-232.
[4]	任杉, 张映锋, 黄彬彬. 生命周期大数据驱动的复杂产品智能制造服务新模式研究[J]. 机械工程学报, 2018, 54(22): 194-203.
[5]	邵景峰, 贺兴时, 王进富, 白晓波, 雷霞, 刘聪颖. 大数据环境下的纺织制造执行系统设计[J]. 机械工程学报, 2015, 51(5): 160-170.
[6]	雷亚国, 贾峰, 周昕, 林京. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
[7]	叶佩青, 张勇, 张辉,. 数控技术发展状况及策略综述[J]. 机械工程学报, 2015, 51(21): 113-120.
[8]	巫江虹, 刘超鹏, 梁志豪, 张才俊. 房间空调器长效运行性能预测及优化方案的研究[J]. 机械工程学报, 2015, 51(18): 158-166.