A knowledge-based approach for detection and diagnosis of out-of-control events in manufacturing processes

Abstract

The authors discuss an approach which combines statistical process control principles and knowledge of the process to arrive automatically at a comprehensive detection and diagnosis of out-of-control conditions in a manufacturing process. This approach consists of capturing data from the process and passing selected signals from it through a two-level decision-making system. The first level of this system involves the use of nonlinear filtering techniques to detect three features (peaks, steps, and ramps) of the input signals. These features are examined to produce a set of out-of-control events. The second level of the process is the application of a rule-set to each event using a backward-chaining algorithm to attempt to diagnose a process cause that led to the event. Status reports of diagnosed and undiagnosed events are generated by the system.<>