Data-driven interpretable fuzzy controller design through mult-objective genetic algorithm
Chia‐Feng Juang, Yu‐Cheng Chang · 2016
This paper considers the problem of data-driven fuzzy controller (FC) design with the objectives of not only high control accuracy but also high interpretability in the control rules. Because the tradeoff between the two objectives, a multi-objective genetic algorithm is employed to find a set of Pareto-optimal FCs. The optimization is based on an initial FC structure online generated through clustering of input data with the input space flexibly partitioned. A constrained objective function is defined to measure fuzzy set transparency and optimization of which improves FC interpretability. Since the dimension of each FC in the parameter solution population changes with the generation of a new rule, a new solution update method is proposed in this paper. The data-driven interpretable fuzzy control approach is applied to control a nonlinear plant in simulation to verify its performance.