Abstract

Machine learning methods have been widely used in different applications, including process control and monitoring. For handling statistical process control (SPC) problems, conventional supervised machine learning methods (e.g., artificial neural networks and support vector machines) would have some difficulties. For instance, a training dataset containing both in-control and out-of-control (OC) process observations is required by a supervised machine learning method, but it is rarely available in SPC applications. Furthermore, many machine learning methods work like black boxes. It is often difficult to interpret their learning mechanisms and the resulting decision rules in the context of an application. In the SPC literature, there have been some existing discussions on how to handle the lack of OC observations in the training data, using the one-class classification, artificial contrast, real-time contrast, and some other novel ideas. However, these approaches have their own limitations to handle SPC problems. In this article, we extend the self-starting process monitoring idea that has been employed widely in modern SPC research to a general learning framework for monitoring processes with serially correlated data. Under the new framework, process characteristics to learn are well specified in advance, and process learning is sequential in the sense that the learned process characteristics keep being updated during process monitoring. The learned process characteristics are then incorporated into a control chart for detecting process distributional shift based on all available data by the current observation time. Numerical studies show that process monitoring based on the new learning framework is more reliable and effective than some representative existing machine learning SPC approaches.

摘要

机器学习方法已广泛用于不同的应用，包括过程控制和监控。对于处理统计过程控制 (SPC) 问题，传统的监督机器学习方法（例如，人工神经网络和支持向量机）会有一些困难。例如，监督机器学习方法需要包含受控和失控 (OC) 过程观察的训练数据集，但它在 SPC 应用程序中很少可用。此外，许多机器学习方法就像黑匣子一样工作。通常很难在应用程序的上下文中解释它们的学习机制和由此产生的决策规则。在 SPC 文献中，已有一些关于如何处理训练数据中缺乏 OC 观察的讨论，使用了一类分类、人工对比、实时对比等一些新颖的思路。然而，这些方法在处理 SPC 问题时有其自身的局限性。在本文中，我们将在现代 SPC 研究中广泛采用的自启动过程监控思想扩展到用于监控具有序列相关数据的过程的通用学习框架。在新框架下，要学习的过程特征是预先明确指定的，并且过程学习是顺序的，即学习的过程特征在过程监控期间不断更新。然后将学习到的过程特征合并到控制图中，用于根据当前观察时间的所有可用数据检测过程分布偏移。