Abstract
Diesel particulate filter (DPF) provides an effective control method for particulate matter (PM) emissions from diesel vehicles. In the PM trap process of DPF, pressure drop and filtration efficiency present conflicting relationships as the main indicators of the comprehensive trap performance. To fully optimize the comprehensive trap performance of DPF, this research develops a hybrid multi-objective optimization approach of FGRA-RF-NSGA III-TOPSIS. Specifically, critical structures are selected from DPF structural features by fuzzy grey correlation analysis (FGRA). Three machine learning (ML) models are trained on the computational fluid dynamics (CFD) model dataset to relate the critical structures to the initial filtration efficiency and pressure drop. Then, statistical indicators are introduced to evaluate three ML models, and the best-performing model – The random forest (RF) model is selected as the input of the optimization algorithm. Finally, a hybrid Critic-TOPSIS approach is used to select the most ideal solution from the Pareto frontier obtained by the NSGA III as the output of the optimization results. The optimized DPF reduces the pressure drop by 49.84 % and improves the initial filtration efficiency by 49.31 % compared to the original DPF under standard operating conditions. The optimization effect is more significant at high-speed and high-load conditions.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have