Fuzzy linguistic control is not computable when one of the control input variables lacks. The missing information can be estimated by the inversion of an «observation-oriented» fuzzy linguistic model, which considers the evolution of the system under fuzzy control. A simple example is presented, which shows that the technique is effective in tracking mode when the precision of the predictive model is sufficient. In regulation mode, when the controlled variable is near the set-point, the observer performance decreases and is more sensitive to disturbances and modelling errors.
Fuzzy control; estimation; model inversion; product-sum-gravity method.
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).