03/19/2024
By Danielle Fretwell

The Francis College of Engineering, Department of Mechanical Engineering, invites you to attend a Doctoral Dissertation defense by Ahmed Almeldein on: Accelerating Chemical Kinetics Calculations of Methane/Air Combustion Using Artificial Neural Networks

Candidate Name: Ahmed Almeldein
Degree: Doctoral
Defense Date: April 1, 2024
Time: Noon to 2 p.m.
Location: Southwick 204

Committee:

  • Advisor: Noah E. Van Dam, Assistant Professor, Mechanical and Industrial Engineering, UMass Lowell
  • J. Hunter Mack, Associate Professor, Mechanical and Industrial Engineering, UMass Lowell
  • Ruizhe Ma, Assistant Professor, Miner School of Computer & Information Sciences, UMass Lowell
  • Pinaki Pal, Senior Research Scientist, Argonne National Laboratory

Brief Abstract:

Accelerating Chemical Kinetics Calculations of Methane/Air Combustion Using Artificial Neural Networks

Detailed chemical kinetics calculations can be very computationally expensive, so various approaches have been used to speed up combustion calculations. Artificial Neural Networks (ANNs) are one promising approach that has seen significant development recently. Despite the increasing effort placed in this area, there are still uncertainties about how best to construct an ANN to reproduce the highly non-linear and numerically stiff system representing chemical kinetics calculations. This study explores different ANN architectures to increase ANN's accuracy while maintaining a moderately small network and dataset sizes.

Two different ANN concepts have been implemented to create an accurate ANN for chemical kinetics applications: Mixture-of-Experts (MoE) and Physics Informed Neural Network (PINN). MoE is a network architecture where multiple sub-networks, i.e., experts, are trained either independently or simultaneously. Then the outputs from those experts are combined to generate the final MOE prediction. The MoE architecture allows the different sub-networks to specialize in different thermochemical regimes, such as pre-ignition, flame front, post-flame, and equilibrium chemistry, reducing the overall size of the network needed compared with a single monolithic network for all conditions. PINNs are a class of neural networks with physical laws embedded within the training process to create networks that follow those physical laws. A new PINN-based DNN approach to chemical kinetics modeling has been developed to incorporate the conservation of atomic species and total energy in the reacting mixture, i.e., summation of all sensible and chemical energy.