Data-driven based multi-objective combustion optimization covering static and dynamic states

作者：

Highlights：

• KELM + MOEA/D strategy is introduced into the data-driven hybrid strategy.

• ARMAX-PSO method is presented to optimize the parameters of PI controller.

• ARMAX + TG-MOEA/D method is proposed to optimize the setpoint.

• The optimization scheme covering multi-objective and different states is proposed.

摘要

•KELM + MOEA/D strategy is introduced into the data-driven hybrid strategy.•ARMAX-PSO method is presented to optimize the parameters of PI controller.•ARMAX + TG-MOEA/D method is proposed to optimize the setpoint.•The optimization scheme covering multi-objective and different states is proposed.

论文关键词：Data-driven,Multi-objective combustion optimization,Machine learning,Evolutionary computation,Closed-loop identification,Optimal control

论文评审过程：Received 10 October 2021, Revised 2 August 2022, Accepted 10 August 2022, Available online 17 August 2022, Version of Record 19 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118531