A PREDICTIVE NEURAL NETWORK MODELING SYSTEM FOR MANUFACTURING PROCESS PARAMETERS

A methodology to predict the occurrence of out-of-control process conditions in a composite board manufacturing facility was developed using neural network theory. Multi-variable regression and time series analysis techniques were applied to analyse the data set for comparison and informational purposes. Regression models were developed to model specific process parameters and could account for only 25% of the variation in those parameters. When analysed as a time series, the data stream was non-stationary in the variance and transformations failed to achieve stationarity. Back-propagation neural networks were successfully trained to represent the process parameters. Inputs to the network consisted of data representing the current process condition along with historical data on relevant parameters, including temperature, moisture content, and bulk density. The training data set was graphically analysed to demonstrate the type of response surface successfully modelled. The trained neural networks were able to successfully predict the state of control of the specific manufacturing process parameters with 70% accuracy, thus, demonstrating the potential of neural networks in manufacturing process analysis.