This research area is focused on development of operative solutions for processing of data acquired from different sources in real time, implementing and applying algorithms for multivariate statistical process monitoring and control (MSPC), in order to generate predictive models to increase the effectiveness and efficiency of industrial processes.
Main Research topics:
-development of quantitative models, based on latent variables, to link product performance to production process settings, raw materials features and structural properties: this includes all aspects going from the use of Experimental Design techniques to improve/optimise formulation, to individuate the critical factors and steps, to the description of the process and its temporal evolution into numerical terms. Finally, using the relevant variables for quantitative raw materials/process properties-product performance relationships studies.
-Implementation of Data Fusion methodologies to integrate information acquired from different sensors and analytical technique
-Studying scalability of Multivariate latent variables model to Big Data
-Multivariate Image analysis for fault detection and identification
-Process Analytical Technologies (PAT)
-Multivariate Statistical Process Control (multivariate and multi-way control charts).
-Multi blocks and multisite data analysis.
-Data Fusion algorithms
Image and signal processing