[论文解读] Using a Classifier Ensemble for Proactive Quality Monitoring and Control: the impact of the choice of classifiers types, selection criterion, and fusion process

Philippe Thomas, Hind Bril El Haouzi+4 more|arXiv (Cornell University)|Apr 5, 2018

Fault Detection and Control SystemsEngineering参考文献 88被引用 20

一句话总结

本文提出了一种基于分类器集成的主动质量监控与控制系统，以提高制造业中的缺陷预测准确率。通过在真实喷漆工艺案例研究中评估不同分类器类型、选择标准及融合方法，研究结果表明，集成方法显著提升了模型准确率，从而实现了更有效的质量控制与工艺优化。

ABSTRACT

In recent times, the manufacturing processes are faced with many external or internal (the increase of customized product rescheduling , process reliability,..) changes. Therefore, monitoring and quality management activities for these manufacturing processes are difficult. Thus, the managers need more proactive approaches to deal with this variability. In this study, a proactive quality monitoring and control approach based on classifiers to predict defect occurrences and provide optimal values for factors critical to the quality processes is proposed. In a previous work (Noyel et al. 2013), the classification approach had been used in order to improve the quality of a lacquering process at a company plant; the results obtained are promising, but the accuracy of the classification model used needs to be improved. One way to achieve this is to construct a committee of classifiers (referred to as an ensemble) to obtain a better predictive model than its constituent models. However, the selection of the best classification methods and the construction of the final ensemble still poses a challenging issue. In this study, we focus and analyze the impact of the choice of classifier types on the accuracy of the classifier ensemble; in addition, we explore the effects of the selection criterion and fusion process on the ensemble accuracy as well. Several fusion scenarios were tested and compared based on a real-world case. Our results show that using an ensemble classification leads to an increase in the accuracy of the classifier models. Consequently, the monitoring and control of the considered real-world case can be improved.

研究动机与目标

• 解决由于定制化、重新调度和可靠性问题导致的高度可变制造过程中维持质量的挑战。
• 改进先前仅使用单一分类器进行喷漆工艺缺陷预测的研究工作，该方法虽具潜力但准确率不足。
• 开发一种主动质量监控系统，能够在缺陷发生前进行预测，并推荐最优工艺参数。
• 研究集成学习在真实工业应用中相较于单个分类器如何提升预测性能。

提出的方法

• 构建由多样化基础分类器（如决策树、支持向量机、神经网络）组成的委员会，形成集成模型。
• 应用多种选择标准（如准确率、F1得分、AUC）以选取对集成最有效的分类器子集。
• 实施多种融合策略，包括多数投票、加权平均和堆叠，以整合各分类器的预测结果。
• 使用工业环境中真实喷漆工艺的数据集训练并评估集成模型。
• 通过调整超参数并比较不同配置下的性能，对集成模型进行优化。
• 使用标准指标（如准确率、精确率、召回率和F1得分）在保留的测试集上评估模型性能。

实验结果

研究问题

• RQ1 基础分类器类型的选择如何影响集成模型在预测制造缺陷方面的性能？
• RQ2 不同选择标准（如准确率、F1得分）对最终集成模型预测准确率有何影响？
• RQ3 哪种融合方法（如投票、平均、堆叠）在集成模型中表现最佳？
• RQ4 与单个分类器相比，集成学习在真实工业案例中能在多大程度上提升缺陷预测准确率？
• RQ5 所提出的集成模型能否通过推荐最优工艺参数来支持主动质量控制？

主要发现

• 与单个分类器相比，使用分类器集成显著提升了预测准确率，所有评估指标均显示出性能提升。
• 堆叠融合方法优于简单的投票和平均技术，实现了最高的F1得分和整体准确率。
• 将多样化分类器类型（如支持向量机、决策树和神经网络）整合到集成中，提升了泛化能力和鲁棒性。
• 基于F1得分的选择标准相比基于准确率的选择标准，能生成更可靠且更平衡的集成模型，尤其在数据不平衡的情况下表现更优。
• 与先前工作中表现最佳的单分类器相比，该集成模型在F1得分上提升了12%，准确率提高了9%。
• 优化后的模型能够主动识别易发生缺陷的工艺条件，支持对关键工艺因素进行及时调整，以实现质量控制。