Fault diagnosis in injection moulding via cavity pressure signals

Abstract

In this paper we demonstrate the feasibility of applying pattern recognition techniques for monitoring and diagnosis to an injection moulding process. Mould cavity pressure signals collected during the process are utilized for monitoring and diagnosis. Principal component analysis is applied to reduce the dimensionality of multivariate signals to a univariate representative signal, while preserving the characteristics of the original signals. Process ‘fingerprints’ are gleaned through wavelet decomposition and multi-resolution analysis of the ‘reduced’ signal. Feature elements defined from these fingerprints are interpreted by an artificial neural network for process condition monitoring and fault diagnosis. The experimental results indicate that this approach is effective for ‘run to run’ process monitoring, diagnostics and control. The diagnostic system can be updated adaptively as new process faults are identified.