Fault detection and diagnosis of a plastic film extrusion process

This paper presents a new approach to the design of a model-based fault detection and diagnosis system for application to a plastic film extrusion process. The design constructs a residual generator via parity relations. A multi-objective optimisation problem must be solved in order for the residual to be sensitive to faults but insensitive to disturbances and modelling errors. In this paper, we exploit a genetic algorithm for solving this multi-objective optimisation problem and the resulting fault detection and diagnosis system is applied to a first-principles model of a plastic film extrusion process. Simulation results demonstrate that various types of faults can be detected and diagnosed successfully.