Dynamic recurrent neural networks for a hybrid intelligent decision support system for the metallurgical industry

Knowledge-based modeling and implementation of the various manufacturing pr ocesses represent an intensive research area. It is known that it is diffic ult to analyze the mechanisms of many industrial production processes and b uild dynamic models by employing classical methods for intelligent systems in manufacturing. This paper describes how to use dynamic recurrent neural networks to provide the model base of a hybrid intelligent system for the m etallurgical industry with a quality control model. The hybrid system extra cts the features of image sequences obtained through the vision detection s ubsystem and employs a dynamic recurrent neural network to assess and predi ct the product qualities to further coordinate the entire production proces s.