Strategy of virtual measurement for optimization of dynamic dead-time processes in automated control systems

This paper presents a new method of virtual measurement of process parameters in the dead-time systems using the virtual adaptive sensor. The method's goal is elimination of the technology-related signal dead-time in automation systems for optimal process control. The additional goal is to make the real-time control possible also in complex processes with dead-time behavior without high development costs. A vacuum coating equipment is considered as an example where the coat thickness is measured by the X-ray fluorescent (XRF) method. It is characterized by significant dead-time that doesn't allow to realize qualitative process control. In order to choose a better strategy to develop the virtual adaptive sensor, the automation process was identified. The simulation of the virtual adaptive sensor on the basis of Artificial Neural Network has shown promising results.