Automatic generation and updating of process industrial digital twins for estimation and control - A review

This review aims at assessing the opportunities and challenges of creating using digital twins for process industrial systems over their life-cycle in context estimation control. The scope is, therefore, to provide a survey on mechanisms generate models machine learning (purely data-driven) automated equation-based modeling. In particular, we consider learning, validation, updating large-scale (i.e., plant-wide or plant-stage but not component-wide) models. These aspects are discussed relation typical application cases value users both operational planning level systems. also connected needed technologies maturity those as given by state art. Combining all aspects, way forward enable automatic generation is proposed, outlining required research development activities. paper outcome project AutoTwin-PRE funded Strategic Innovation Program PiiA within Swedish Agency VINNOVA academic version an industry report prior published PiiA.