【作者】 李泽华； 赵春晖； 王伟；

【Author】 LI Ze-hua;ZHAO Chun-hui;WANG Wei;Department of Control Science and Engineering,Zhejiang University;China Tobacco Zhejiang Industrial Co.,Ltd.;

【机构】 浙江大学控制科学与工程学院； 浙江中烟工业有限责任公司；

【摘要】 近些年,频繁发生的产品召回事件,愈发体现出产品质量追溯的重要性。然而,传统的质量追溯方法缺乏对于造成质量问题的关键因素的有效分析,难以满足实际工业生产的需求。针对这一问题,本文提出一种稀疏偏最小二乘-典型相关分析(SPLS-CCA)的产品质量智能追溯方法,实现了影响产品质量的关键过程变量的有效分析与识别,从而为后续提高产品质量提供了依据。这一方法对于企业的产品质量把控与经济效益的提高有着较大的意义。更多还原

【Abstract】 In recent years, frequent product recalls have increasingly necessitated the importance of product quality tracing. However, the traditional quality tracing method lacks an effective analysis of the key factors that cause quality defect, and it is difficult to meet the demands of actual industrial production. In order to solve this problem, this paper proposes a sparse partial least squares-canonical correlation analysis(SPLS-CCA) method for intelligent product quality tracing, which realizes effective analysis and identification of key process variables that affect product quality and provides a basis for the following improvement of product quality. This method is of significance for the enterprise’s product quality and economic benefit.更多还原