Decision surface modeling of textile spinning operations using neural network technology

The authors study the spinning operations in textile manufacturing. An attempt to "metamodel" the relation between key inputs and performance measures using neural network technology is reported. Two different neural network models, namely a backpropagation neural network and a fuzzy control neural network, were investigated. According to their experience, both models are capable of providing high quality predictions. In addition, results obtained using a fuzzy controller for the learning rate suggest a significant potential for speeding up the training process.<>