Artificial Intelligence and Data Driven Optimization of Internal Combustion Engines

Jihad Badra is the Engine Combustion Team leader in the Transport Technologies Research and Development Division at Saudi Aramco. He joined Saudi Aramco in 2014 after working as a Postdoctoral Researcher in the Clean Combustion Research Center at King Abdullah University of Science and Technology (KAUST). Jihad’s research interest is in developing and optimizing internal combustion engine technologies with decreased net environmental impact. Jihad’s current focus is on fuel formulation for advanced engines and engine modelling using computational fluid dynamics. Jihad has more than 50 peer-reviewed journal papers. Jihad received his BASc in Mechanical Engineering from the University of Balamand, Lebanon and MASc and PhD degrees in Combustion Research in Mechanical Engineering at the University of Sydney, Australia. Pinaki Pal is a research scientist in Argonne’s Energy Systems division. His research interests broadly lie in the areas of computational fluid dynamics (CFD), turbulent combustion modeling, machine learning, computational science, and high-performance computing, for a wide range of applications, such as propulsion (automotive and aerospace) and material synthesis. Dr. Pal received his PhD from University of Michigan-Ann Arbor (2015) in Mechanical Engineering, with specialization in turbulent combustion modeling and CFD for low temperature combustion applications in both internal combustion engines and gas turbines. He also holds a Bachelor of Technology in Mechanical Engineering from the Indian Institute of Technology Kharagpur (India) (2011). Yuanjiang Pei is a Technical Specialist at Aramco Americas: Aramco Research Center – Detroit working on the co-optimization of fuels and engines in pursuit of higher internal combustion engine efficiency. Pei has more than 10 years of experience working in the engine research and automotive industry. He joined Aramco in late 2015 after previously working more than 2 years on engine combustion modeling at Argonne National Laboratory and 5 years on engine management system calibration and project management at Delphi. Pei is actively involved in the organization of several international conferences, including Society of Automotive Engineers (SAE) World Congress, American Society of Mechanical Engineers (ASME) Internal Combustion Engine Fall (ICEF) Conference and Engine Combustion Network (ECN) workshops. Sibendu Som is the manager of the Computational Multi-Physics Research Section in the Energy Systems Division at Argonne National Laboratory and a senior scientist at the Consortium for Advanced Science and Engineering, University of Chicago. Dr. Som has over a decade of experience in enabling technologies for more efficient engine combustion using computational tools. He leads a Computational Fluid Dynamics (CFD) team at Argonne National Laboratory with a research focus on the development of nozzle-flow, spray, and combustion models, using high-performance computing (HPC) for internal combustion engine (ICE) applications. His team is responsible for developing predictive simulation capabilities to enable OEMs to develop advanced high-efficiency, low-emission engines. Dr. Som’s group is pioneering the implementation of machine learning (ML) techniques to further speed up piston engine and gas turbine simulations. He is a co-founder and technical lead of Argonne’s Virtual Engine Research Institute and Fuels Initiative (VERIFI) program, which is aimed at providing predictive simulations for industry. Dr. Som and his team are recognized worldwide for improving the predictive capability of simulation tools and applying these tools using HPC to reduce time to design.

1. Active-learning for fuel optimization 2. High throughput screening for fuel formulation 3. Engine optimization using computational fluid dynamics-Genetic algorithms (CFD-GA) 4. Engine optimization using computational fluid dynamics-design of experiments (CFD-DoE) 5. Engine optimization using machine learning-genetic algorithms (ML-GA) 6. Machine learning driven sequential optimization using dynamic exploration and exploitation 7. Optimization of after-treatment systems using machine learning 8. Engine cycle-to-cycle variation control 9. Prediction of low pressure preignition using machine learning 10. AI aided optimization of experimental engine calibration 11. AI aided optimization of vehicle control calibration