A new skeletal mechanism for simulating MILD combustion optimized using Artificial Neural Network

• Published in: Energy (Oxford) Vol. 237; p. 121603
• Main Authors: Si, Jicang, Wang, Guochang, Li, Pengfei, Mi, Jianchun
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 15.12.2021; Elsevier BV
• Subjects: Artificial Neural Network (ANN); Artificial neural networks; Combustion; Computational fluid dynamics; Computer applications; energy; Flame propagation; Jet flow; Mechanism reduction; Methane; MILD combustion; Neural networks; Optimization; Premixed flames; Reduction; Singular perturbation; Skeletal mechanism; Spontaneous combustion; Mechanism reduction; Skeletal mechanism; MILD combustion; Artificial Neural Network (ANN)
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2021.121603

This work develops a new skeletal mechanism of methane MILD combustion by a joint method of Directed Relation Graph (DRG), Computational Singular Perturbation (CSP) and Artificial Neural Network (ANN) (abbreviated as DRG-CSP-ANN method), where DRG and CSP are used for mechanism reduction and ANN for optimization. The detailed mechanism GRI-3.0, containing 53 species and 325 elementary reactions, is simplified to a skeletal mechanism with only 13 species and 35 reactions, named as Reduced-ANN. In addition, the mechanism reduced by DRG-CSP without ANN optimization, called Reduced-Ori, is also considered for comparison. Subsequently, the Reduced-ANN is validated by comparing its performance with those of other skeletal mechanisms, against that of GRI-3.0, in the auto-ignition time, one-dimensional premixed flame propagation speed and different computational-fluid-dynamics (CFD) simulations (i.e., CH4/H2 jet flame in hot coflow, premixed and non-premixed in-furnace MILD combustion). Results show that Reduced-ANN performs significantly better than all the other skeletal mechanisms including Reduced-Ori. For instance, the use of Reduced-ANN lessens the errors of predicting autoignition time and flame propagation speed from 7-18 % to 1.4 % and 16 % to 4 %, respectively. Therefore, the DRG-CSP-ANN method is qualified as a very promising way for mechanism reduction. In addition, the unsatisfying performance of Reduced-Ori demonstrates the necessity of mechanism optimization in reduction work, so that better predictions of specific quantities can be made to match those by the detailed mechanism. •Reducing the detailed mechanism GRI-3.0 to a skeletal mechanism for simulating MILD combustion.•Using Artificial Neural Network (ANN) to learn and correct the skeletal mechanism for optimizing various parameters.•Comparing new model, Reduced-ANN, with other skeletal mechanisms against GRI-3.0.•Demonstrating Reduced-ANN to perform far better than any of other skeletal mechanisms.•Increasing prediction accuracy of autoignition time or flame propagation speed by up to 13 or 4 times.