基于典型相关分量组的多元工序质量相关性诊断算法1algorithmof.pdfVIP

基于典型相关分量组的多元工序质量相关性诊断算法1 牛 青，莫 蓉，万 能 （西北工业大学 现代设计与集成制造技术教育部重点实验室，陕西 西安 710072） 摘要：针对制造过程中的多元工序质量相关性诊断问题，提出了一种基于典型相关分量组的诊 断算法。首先利用相关性分解定理，将质量分量的总体相关关系分解为一系列分量对之间的相关关 系；然后以分量对之间相关关系的传递性为依据，将全部分量对之间的相关关系通过一组典型相关 分量对之间的相关关系进行表示；最后提出了基于最大相关树的最优典型相关分量组求解算法，并 2 针对全部最优典型相关分量对，建立T 控制图，构成多元工序质量相关性诊断模型。理论分析和实 验表明，基于典型相关分量组的工序质量相关性诊断算法能够有效减小诊断体系的规模，提高诊断 效率，并能有效消除诊断信息的冗余性。 2 关键词：多元工序质量；相关性诊断；典型相关分量对；最大相关树；T 控制图 + 中图分类号：TH165 .4 文献标识码：A Algorithm of correlation diagnosis in multivariate process quality based on typical correlated components group NIU Qing,MO Rong,WAN Neng （Key Laboratory of Contemporary Design and Integrated Manufacturing Technology，Ministry of Education，Northwestern Polytechnical University，Xi’an 710072，China） Abstract: Aiming at the problem of correlation diagnosis in multivariate process quality management, an algorithm based on typical correlated component pairs group is proposed. Firstly, by using the theorem of correlation decomposition, correlation of all quality components is decomposed as a series of correlations of component pairs, and then the decomposition results can be represented by a correlations set of typical component pairs group according to the transitivity of component pairs’correlations. Finally, algorithm of the optimal typical correlated component pairs group based on maximum correlation spanning tree is proposed, and T2 control charts of typical component pairs are established to form the correlation diagnosis model. Theoretical analysis and practice prove that the proposed algorithm could reduce the scale of diagnosis system and eliminate the redundancy of diagnostic messages effec