Automated design of an Unscented Kalman Filter for state- and parameter estimation on unknown models

Abstract

Ever higher demands on modern mechatronic systems, along with increasing complexity and high development pressure, require a high degree of automation in the model-based development process. An automated generation of topology-oriented models on the basis of requirements, solution patterns, and solution elements poses new challenges to the design and application of state- and parameter estimators for control and condition monitoring. This paper presents a methodology for a highly automated integration of such models into a filter that can be used in real time for state- and parameter estimation as well as the layout of this filter. There need not be any expert knowledge of the underlying model or the algorithms of the filter. The presented methodology and applied tools are able to avoid the drawbacks of established procedures while achieving a considerably higher accuracy in the results