Grey-box Process Control Mining for Anomaly Monitoring and Deconstruction

TL;DR

This paper introduces a grey-box anomaly detection method for smart manufacturing that combines physical process models with statistical analysis to improve detection and interpretability of anomalies in semiconductor wafer production.

Contribution

The paper presents a novel grey-box approach that integrates control system physics with Bayesian regression to derive shape signatures for anomaly detection and source identification.

Findings

Effective anomaly detection in wafer manufacturing processes.

Ability to deconstruct anomaly scores to identify contributing parameters.

Enhanced process insight through shape signature analysis.

Abstract

We present a new "grey-box" approach to anomaly detection in smart manufacturing. The approach is designed for tools run by control systems which execute recipe steps to produce semiconductor wafers. Multiple streaming sensors capture trace data to guide the control systems and for quality control. These control systems are typically PI controllers which can be modeled as an ordinary differential equation (ODE) coupled with a control equation, capturing the physics of the process. The ODE "white-box" models capture physical causal relationships that can be used in simulations to determine how the process will react to changes in control parameters, but they have limited utility for anomaly detection. Many "black-box" approaches exist for anomaly detection in manufacturing, but they typically do not exploit the underlying process control. The proposed "grey-box" approach uses the process-control ODE model to derive a parametric function of sensor data. Bayesian regression is used to fit the parameters of these functions to form characteristic "shape signatures". The probabilistic model provides a natural anomaly score for each wafer, which captures poor control and strange shape signatures. The anomaly score can be deconstructed into its constituent parts in order to identify which parameters are contributing to anomalies. We demonstrate how the anomaly score can be used to monitor complex multi-step manufacturing processes to detect anomalies and changes and show how the shape signatures can provide insight into the underlying sources of process variation that are not readily apparent in the sensor data.