Time series forecasting by means of SOM aided Fuzzy Inference Systems

Abstract

The forecast of industrial process time series represents a critical factor in order to assure a proper operation of the whole manufacturing chain, as it allows to act against any process deviation before it affects the final manufactured product. In this paper, in order to take advantage from process relations and improve forecasting performance, a prediction method based in Adaptive Neuro Fuzzy Inference System (ANFIS) and Self-Organizing Maps is presented. The novelties of the proposed method are based on considering, as an input of an ANFIS model, the interrelations of process variables regarding the signal that wants to be forecasted, by means of topology preservation SOM. An experimental study performed with real industrial data from a cooper manufacturing plant indicated the suitability of the proposed method in time series forecasting applications.

Industrial process monitoring by means of recurrent neural networks and Self Organizing Maps

“…These new approaches are aimed to improve the control of the plants by means of extracting actionable knowledge from the internal mechanics of the machines [2]. A deviation from the nominal working parameters implies a divergence from the optimal production specification and a misalignment from the best product quality point, effectively causing a critical loss of potential earnings [3]. Thus, the manufacturing industry as a whole, and more so in Europe, is striving towards the Zero Defects Manufacturing (ZDM) paradigm [4].…”