Integrating supervised and unsupervised learning approaches to unveil critical process inputs

TL;DR

This paper presents a machine learning framework combining unsupervised clustering and supervised models to identify critical process inputs and predict outcomes in large-scale industrial processes, exemplified by a chemical vapor deposition case.

Contribution

It introduces a novel approach that merges clustering and supervised learning to determine key inputs and improve prediction accuracy in complex industrial settings.

Findings

Identified critical inputs influencing process outcomes.

Effectively clustered production runs based on qualitative characteristics.

Enhanced prediction of production outcomes with limited data.

Abstract

This study introduces a machine learning framework tailored to large-scale industrial processes characterized by a plethora of numerical and categorical inputs. The framework aims to (i) discern critical parameters influencing the output and (ii) generate accurate out-of-sample qualitative and quantitative predictions of production outcomes. Specifically, we address the pivotal question of the significance of each input in shaping the process outcome, using an industrial Chemical Vapor Deposition (CVD) process as an example. The initial objective involves merging subject matter expertise and clustering techniques exclusively on the process output, here, coating thickness measurements at various positions in the reactor. This approach identifies groups of production runs that share similar qualitative characteristics, such as film mean thickness and standard deviation. In particular, the differences of the outcomes represented by the different clusters can be attributed to differences in specific inputs, indicating that these inputs are critical for the production outcome. Leveraging this insight, we subsequently implement supervised classification and regression methods using the identified critical process inputs. The proposed methodology proves to be valuable in scenarios with a multitude of inputs and insufficient data for the direct application of deep learning techniques, providing meaningful insights into the underlying processes.