Nonlinear prediction of manufacturing systems through explicit and implicit data mining

Abstract

Many processes in the industrial realm exhibit stochastic and nonlinear behavior. Consequently, an intelligent system must be able to adapt to nonlinear production processes as well as probabilistic phenomena. To this end, an intelligent manufacturing system may draw on techniques from disparate fields, involving knowledge in both explicit and implicit form. In order for a knowledge based system to control a manufacturing process, an important capability is that of prediction: forecasting the future trajectory of a process as well as the consequences of the control action. This paper presents a comparative study of explicit and implicit methods to predict nonlinear chaotic behavior. The evaluated models include statistical procedures as well as neural networks and case based reasoning. The concepts are crystallized through a case study in the prediction of chaotic processes adulterated by various patterns of noise. (C) 1997 Elsevier Science Ltd.