Preprint: Multi-objective Evolutionary Algorithm for the Optimization of Noisy Combustion Processes

TL;DR: This work introduces a multi-objective evolutionary algorithm capable of handling noisy problems with a particular emphasis on robustness against unexpected measurements (outliers) based on the Strength Pareto Evolutionary Algorithm of Zitzler and Thiele.

Abstract: Evolutionary Algorithms have been applied to single and mul- tiple objectives optimization problems, with a strong emphasis on problems, solved through numerical simulations. However in several engineering problems, there is limited availability of suitable models and there is need for optimization of realistic or experimental configurations. The multi- objective optimization of an experimental set-up is addressed in this work. Experimental setups present a number of challenges to any optimization technique including: availability only of pointwise information, experimen- tal noise in the objective function, uncontrolled changing of environmental conditions and measurement failure. This work introduces a multi-objective evolutionary algorithm capable of handling noisy problems with a particular emphasis on robustness against unexpected measurements (outliers). The algorithm is based on the Strength Pareto Evolutionary Algorithm (SPEA) of Zitzler and Thiele and includes the new concepts of domination dependent lifetime, re-evaluation of solutions and modifications in the update of the archive population. Sev- eral tests on prototypical functions underline the improvements in conver- gence speed and robustness of the extended algorithm. The proposed algorithm is implemented to the Pareto optimization of the combustion process of a stationary gas turbine in an industrial setup. The Pareto front is constructed for the objectives of minimization of NOx emis- sions and reduction of the pressure fluctuations (pulsation) of the flame. Both objectives are conflicting affecting the environment and the lifetime of the turbine, respectively. The optimization leads a Pareto front corre- sponding to reduced emissions and pulsation of the burner. The physical implications of the solutions are discussed and the algorithm is evaluated. Keywords—evolutionary algorithms, multi-objective optimization, noisy objective functions, gas turbine combustion, emission reduction, combus- tion instabilities