VISBREAKER ANALYSIS BY MULTIDIMENSIONAL SCALING

Advanced monitoring of critical industrial processes for high quality, safety, economy is favoured by software applications strengthening human-computer interaction. In real industries processes have hundreds of variables to be followed and monitoring should be done in a 2-D or 3-D spaces by space reduction. For this purpose, space reduction must keep the relevant and informative geometric characteristics of the original space, using proper metrics. In this work, the reduction of n-dimensional space to bi or tri-dimensional one is developed through multidimensional scaling. In the 2-D or 3-D process map, the operational regions of the process under specific conditions can be classified. This classification is made by clustering. This strategy is applied to the large-scale process of Visbreaker, from Refinery of Petrogal at Sines (Galp Energia), using multidimensional scaling with several metrics.