复杂产品关键质量特性识别方法

工业工程 ›› 2012, Vol. 15 ›› Issue (3): 75-79.

复杂产品关键质量特性识别方法

天津大学管理与经济学部，天津 300072

出版日期:2012-06-30 发布日期:2012-07-21
作者简介:闫伟(1982-)，男，河北省人，博士研究生，主要研究方向为工业工程、质量工程.
基金资助:
国家自然科学基金重点资助项目（70931004）；国家科学自然科学基金资助项目（71002105）

Research on Identification of Critical-to-Quality Characteristics for Complex Products

College of Management and Economics，Tianjin University, Tianjin 300072，China

Online:2012-06-30 Published:2012-07-21

摘要/Abstract

摘要： 在复杂产品的关键质量特性（criticaltoquality characteristics, CTQ）识别中，传统方法应用于不平衡数据时会表现出有偏性，即对占类别比例较小的不合格产品识别的性能明显劣于占比例较大的合格样本。为解决以上问题，提出了基于改进信息增益（information gain,IG）算法的复杂产品高维不平衡数据集CTQ识别方法，利用改进IG算法评价标准降低不平衡数据中有偏性的影响，从而有效识别CTQ。算例结果表明该方法可以显著提高不平衡数据关键质量特性识别性能。

关键词: 复杂产品, 关键质量特征, 信息增益

Abstract: Often, most of products to be inspected are qualified, and only a small fraction is unqualified. In other words, the number of qualified and unqualified products are highly unbalanced. In the identification of criticaltoquality characteristics (CTQ), significant performance deviation is observed when traditional method is applied. The performance of identifying CTQ for the unqualified products is significantly inferior to that for the qualified products. In order to solve problem, improved information gain (IG) algorithm is proposed to process such highdimension imbalance data. By this method, it reduces the influence of imbalance data on the performance such that the identification of CTQ is significantly improved. Numerical simulation for an example verifies the effectiveness of the proposed method.

Key words: complex products, criticaltoquality characteristics (CTQ), information gain (IG)

闫伟，何桢，田文萌. 复杂产品关键质量特性识别方法[J]. 工业工程, 2012, 15(3): 75-79.

Yan Wei， He Zhen， Tian Wenmeng. Research on Identification of Critical-to-Quality Characteristics for Complex Products[J]. Industrial Engineering Journal , 2012, 15(3): 75-79.

参考文献

［1］李伯虎.复杂产品制造信息化的重要技术——复杂产品集成制造系统［J］.中国制造业信息化,2006(7):19-23. Li Bohu.Important technical of complex products manufacturing information complex products integrated manufacturing system［J］.Manufacture Information Engineering of China, 2006(7):19-23. ［2］宋晓宇,刘锋,孙焕良.基于粗糙集的聚类算法中阈值自动选取［J］.系统工程与电子技术,2010,32(1):192-194. Song Xiaoyu,Liu Feng,Sun Huanliang. Autonomous threshold selection based on rough set theory in clustering algorithm［J］.Systems Engineering and Electronics, 2010,32(1):192-194. ［3］Yan W,He Z,Tian W M.The application of relief algorithm for identifying CTQ in complex products［C］.2011 2nd IEEE International Conference on Emergency Management and Management Sciences.Beijing:BUCT,2011:459-460. ［4］Sotiris K, Dimitris K, Panayiotis P. Handling imbalanced datasets: A Review［J］. Robotics and Computer integrated Manufacturing, 2005, 21(2): 559-567. ［5］Don J Lee, Anna C Thornton, The identification and use of key characteristics in the product development process［C］. Proceedings of the ASME Design Engineering Technical Conferences and Computers in Engineering Conference. California:Irvine,1996: 211-217. ［6］蒋良孝.一种基于信息增益的分类规则挖掘算法［J］.中南工业大学学报,2003,34(2):69-71. Jiang Liangxiao. A classification rule mining algorithm based on the information gain［J］.Journal of South University,2003,34(2):69-71. ［7］Japkowicz N,Stephen S. The class imbalance problem: a systematic study［J］.Intelligent Data Analysis,2002,6(5):203-231．［8］Marko R,Igor K.Theoretical and empirical analysis of reliefF and rreliefF［J］.Machine Learning,2003,53(6):23-69. ［9］Kubat M, Matwin S.Addressing the curse of imbalanced training sets: onesided selection［C］. Proceedings of the Fourteenth International Conference on Machine Learning. Nashville:Morgan Kaufman,1997:179-186. ［10］Smad F.Retrieving collocation from text:xtract［J］.Computational Linguistics,1993,19(1):143-175. ［11］Church K.Word Association norms mutual information and lexicography［J］.Computational Linguistics,1990,16(1):22-29. ［12］Elkan C.The Foundations of cost-sensitive learning［C］.Proceedings of the 17th International Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufman,2001:973-978. ［13］Domingos P.MetaCost:a general method for making classifiers cost-sensitive［C］.Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego:ACM,1999:155-164. ［14］Fan W,Stolfo S J,Zhang J X.AdaCost: misclassification cost-sensitive boosting［C］.Proceedings of the 16th International Conference on Machine Learning.Bled:Morgan Kaufman,1999:97-105. ［15］Murphy P, Aha D.UCIML repository secom dataset［EB/OL］.(2008). http:∥archive.ics.uci.edu/ml/machine learning-databases/secom.