Nonlinear plants with derived Takagi–Sugeno–Kang plant models can be successfully controlled by model-based fuzzy logic controllers built as parallel distributed compensation (PDC). The PDC simple structure of a few fuzzy rules facilitates both the design based on the well-mastered linear control technique and the real time industrial implementation via programmable logic controllers. The novelty of the present research is the optimisation of the PDC tuning parameters in order to improve the performance of the closed-loop system for the control of the liquid level in a carbonisation column for soda ash production. A multiobjective optimisation is carried out off-line using genetic algorithms and simulations. The improvement of the closed-loop system dynamic accuracy and the reduction of the control action variance for saving lifetime of the expensive control valve are assessed via simulation and real time industrial experiments in comparison to the system with the tuned by classical approaches PDC.