We are proud to announce our latest collaborative publication in Energy and Fuels.
This new paper reports the development of a fuel-flexible engine modeling framework. By integrating a computationally efficient Quasi-Dimensional approach with fuel-sensitive combustion models including our ML-based laminar flame speed model, this research provides a new method for evaluating the impact of fuel characteristics on combustion behavior in internal combustion engines.
This achievement was made possible through a fantastic multi-institutional collaborative effort. We extend our gratitude to our co-authors and partners: Prof. Boehman at the University of Michigan, Prof. Han at the University of Suwon, and our own Prof. Jung and Dr. Kwak here at UM-Dearborn.
Congratulations to the entire research team on this excellent work!
https://pubs.acs.org/doi/abs/10.1021/acs.energyfuels.6c00269
We are thrilled to announce that Vijay has won both Second and Third Place at the University of Michigan's Empowering Research with AI Awards! Hosted by the AI Institutes at Michigan (AIIM), this university-wide competition recognizes researchers who are driving discoveries through the innovative use of artificial intelligence. Out of more than 180 submissions across U-M's campuses, taking home two of these competitive awards is a fantastic testament to Vijay’s hard work.
Vijay earned Second Place for his independent research conducted prior to joining UM-Dearborn, titled "AgriTwin: An Attention-Based Multimodal Deep Learning Framework for Simultaneous Yield and Price Forecasting in U.S. Specialty Crops," which was also selected for an oral presentation. Additionally, he secured Third Place and a poster presentation for our lab's engine modeling work, "Toward Fuel-Flexible Engine Digital-Twins Enabled by Machine Learning."
Congratulations Vijay!
https://record.umich.edu/articles/aiim-awards-86-research-teams-for-innovative-uses-of-ai/
Congratulations to Vijay on his first publication with our lab! Our latest paper, recently published in Applications in Energy and Combustion Science, successfully utilizes a bagged ensemble of ANN to predict the laminar flame speed of gasoline surrogate fuels and syngas blends. This not only highlights Vijay's excellent work but also marks our group's very first achievement in integrating machine learning techniques with fundamental combustion modeling.
https://www.sciencedirect.com/science/article/pii/S2666352X25000718
We are excited to share our latest research publication, "Electro-Thermal Modeling and Parameter Identification of an EV Battery Pack Using Drive Cycle Data," recently published in the journal Batteries. This paper leverages real-world drive cycle data to improve the accuracy of electro-thermal models for electric vehicles. This work provides valuable insights for developing safer and more efficient battery management systems for future mobility.