Stream-Based Active Learning for Process Monitoring

TL;DR

This paper introduces a stream-based active learning approach that improves process monitoring by efficiently classifying process states, especially in scenarios with limited labels and evolving out-of-control conditions.

Contribution

It develops a novel active learning strategy that enhances partially hidden Markov models for dynamic, resource-efficient process state classification in industrial settings.

Findings

Effective in classifying process states with limited labeled data

Handles class imbalance and unseen out-of-control states

Validated through simulation and automotive case study

Abstract

Statistical process monitoring (SPM) methods are essential tools in quality management to check the stability of industrial processes, i.e., to dynamically classify the process state as in control (IC), under normal operating conditions, or out of control (OC), otherwise. Traditional SPM methods are based on unsupervised approaches, which are popular because in most industrial applications the true OC states of the process are not explicitly known. This hampered the development of supervised methods that could instead take advantage of process data containing labels on the true process state, although they still need improvement in dealing with class imbalance, as OC states are rare in high-quality processes, and the dynamic recognition of unseen classes, e.g., the number of possible OC states. This article presents a novel stream-based active learning strategy for SPM that enhances partially hidden Markov models to deal with data streams. The ultimate goal is to optimize labeling resources constrained by a limited budget and dynamically update the possible OC states. The proposed method performance in classifying the true state of the process is assessed through a simulation and a case study on the SPM of a resistance spot welding process in the automotive industry, which motivated this research.