A novel, robust, fast, user-friendly advisory system will be delivered. It will support operators of complex processes in making decisions. The system will guide them through high-dimensional noisy heterogeneous data spaces to successful areas. It will also warn them against dangerous areas. The project will (i) complete the consistent novel probabilistic theory of dynamic adaptive clustering and theory of advising (ii) create and thoroughly test the full set of robust and fast algorithms covering both experience accumulation and on-line advising to operators (iii) prepare adequate interaction sessions suitable for process staff (iv) implement the advisory systems with an intelligent graphical interface tailored to industrial environment (v) demonstrate the power of the tool on a full scale, cold-rolling mill application (vi) demonstrate generic nature of the tool on data taken from other sites and fields (transportation, glass industry and medicine).