Algorithmic Statistical Process Control: Concepts and an Application

TLDR

The methodology seeks to merge automatic control and statistical process control—fields that have evolved separately—by building on prior work to cover statistical identification, modeling, feedback control, and final SPC monitoring. The study aims to reduce predictable quality variations through feedback and feedforward techniques and to monitor the system for unexpected root causes. It integrates statistical identification and modeling with feedback control and SPC monitoring, employing feedback/feedforward methods to lower predictable variations while addressing operational and technical issues in a general framework. Experience controlling intrinsic viscosity in a GE polymerization process demonstrated that SPC and feedback control can be unified into a single system.

Abstract

The goal of algorithmic statistical process control is to reduce predictable quality variations using feedback and feedforward techniques and then monitor the complete system to detect and remove unexpected root causes of variation. This methodology seeks to exploit the strengths of both automatic control and statistical process control (SPC), two fields that have developed in relative isolation from one another. Recent experience with the control and monitoring of intrinsic viscosity from a particular General Electric polymerization process has led to a better understanding of how SPC and feedback control can be united into a single system. Building on past work by MacGregor, Box, Astrom, and others, the article covers the application from statistical identification and modeling to implementing feedback control and final SPC monitoring. Operational and technical issues that arose are examined, and a general approach is outlined.