MONITORING THE PROCESS OF CURING OF EPOXY GRAPHITE FIBER COMPOSITES WITH A RECURRENT NEURAL-NETWORK AS A SOFT SENSOR/

Controlling the curing of fiber-reinforced composites involves an on-l ine evaluation of their properties such as viscosity, resin content, a nd degree of cure (DOC). Infrared spectroscopic and dielectric sensors have commonly been considered for monitoring these properties. Nevert heless, they are expensive, and yet do not yield a precise cure histor y during the entire process. Artificial neural networks have successfu lly been adopted for the dynamic modeling of nonlinear systems. Inasmu ch as the actual DOC of a composite cannot readily be measured in situ during the cure, long-term prediction of the DOC is critical. In the present study, a unique integrated sensor has been constructed that co mprises a dual heat-flux sensor serving as a hard sensor for determini ng the Damkohler number (Da) and a recurrent neural network (RNN) serv ing as a soft sensor for evaluating and predicting the DOC on the basi s of the Da obtained. At the outset, the prototype soft sensor, i.e., RNN, was configured through a series of repeated and rapid simulations of an analogous model system with known performance equations for lea rning and testing. Subsequently, this prototype RNN was tuned and vali dated through a minimum number of laborious experiments,so that the re sultant soft sensor is capable of effectively monitoring on-line the D OC of the prepreg of a commercial epoxy/graphite fiber composite in a bag-molding process. (C) 1998 Elsevier Science Ltd. All rights reserve d.