Identification of Numerically Accurate First-Order Takagi-Sugeno Systems with Interpretable Local Models from Data
Andri Riid, and Ennu Rüstern
Department of Computer Control, Tallinn University of Technology, Ehitajate tee 5, Tallinn 19086, Estonia
The paper deals with the interpretability problem of 1st order Takagi-Sugeno systems and interpolation issues in particular. Interpolation is improved by a corrective secondary model – essentially a black box – complementing the primary (interpretable) model. Optimization technique for this two-model configuration is developed. Experimental results indicate that the approach achieves a better accuracy-interpretability tradeoff than methodologies currently in use.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.