Autoassociative Neural Networks in Bioprocess Condition Monitoring

Abstract Statistical Process Control procedures are receiving significant attention in response to increasing demands for improved bioprocess performance and reproducibly high levels of quality product. In particular the multivariate statistical approaches of partial least squares and principal component analysis have been addressed in order to provide for efficient predictive model development from highly dimensioned and ill conditioned monitored process data. This contribution addresses an alternative approach using artificial neural networks to provide a nonlinear model. In particular the problem of process fault detection is considered using a feature detection network topology to reduce the dimensionality of the problem and extract from the process data important attributes that indicate the presence of process malfunctions. The ability of the method to detect process faults is demonstrated by applications to two industrial bioprocesses.