Vispi Nevile Karkaria

Machine Learning, Digital Twins, Time-Series Analysis, Optimization

As a Ph.D. student at Northwestern University, my focus is centered on the development and implementation of machine learning algorithms for Digital Twins. I'm deeply immersed in projects encompassing various fields such as time-series analysis, language models, deep learning, uncertainty quantification, and optimization. My proficiency lies in creating machine learning models specifically designed for time-series analysis and building optimization algorithms for real-time decision making. My research is predominantly oriented toward the creation and utilization of these algorithms to construct digital twin systems. The concept of a digital twin refers to the creation of a digital replica of a physical system. This virtual model is capable of learning from its real-life counterpart in real time, facilitating instantaneous decision making by providing actionable feedback to the physical system. The harmony between the physical and digital systems encapsulates the innovative and dynamic nature of my research.

Education

Northwestern University
Ph.D., Mechanical Engineering
2021 - Present
Advisor: Prof. Wei Chen (Mechanical Eng.), GPA: 3.88/4
College of Engineering, Pune (CoEP)
B.Tech., Mechanical Engineering
2018 - 2021
Thesis: Digital Twin Manufacturing of Composite Material
Cusrow Wadia Institute of Technology
Diploma in Engineering, Mechanical Engineering
2015 - 2018
Thesis: Forward Reverse Motion Multi-Cylinder Ball Milling Machine

Projects

Development of a Tire Lifespan Predictive Algorithm via Random Forest

2021-2023

Algorithms: Random Forest, Gaussian Process Models, Data Balancing Methods

  • Conceived and developed a robust machine learning pipeline with a Random Forest model, leading to successful prediction of tire lifespan.
  • Introduced the novel Variance Reduction Synthetic Minority Oversampling Technique (VR-SMOTE) for effective data balancing, yielding superior results over conventional and contemporary balancing methods.

Designing LSTM Model for Streamlining Additive Manufacturing Process

2022-2023

Algorithms: LSTM, Deep Learning, Big Data

  • Architected an LSTM-based machine learning model that acts as a surrogate for the Additive Manufacturing Process, delivering significant reduction in prediction time.
  • Developed a comprehensive Big Data management system to efficiently handle the extensive data generated during the process.

Development of Latent-Variable Constrained Bayesian Optimization (LV-CBO)

2022-2023

Algorithms: Mixed Variable Optimization, Gaussian Processes, PyTorch

  • Engineered a Bayesian optimization algorithm incorporating Latent Variables that adeptly handles both continuous and categorical variables.
  • The LV-CBO algorithm effectively tackled complex optimization challenges faced by Hyundai Motor Company.

Formulation of Machine Learning Model to Enhance the Lifespan of Super-Capacitors

2020-2023

Algorithms: Deep Learning, Gaussian Processes, PyTorch

  • Designed a deep learning algorithm capable of predicting current output under various configurations.
  • Leveraged gradient-based optimization techniques to determine the most efficient super-capacitor design through a data-driven approach.

Publications

An optimization-centric review on integrating artificial intelligence and digital twin technologies in manufacturing

Authors: Karkaria, Vispi, Ying-Kuan Tsai, Yi-Ping Chen, and Wei Chen.

Engineering Optimization, 2024, pp. 1-47. Paper Link

Towards a Digital Twin Framework in Additive Manufacturing: Machine Learning and Bayesian Optimization for Time Series Process Optimization

Authors: Karkaria, V., Goeckner, A., Zha, R., Chen, J., Zhang, J., Zhu, Q., Cao, J., Gao, R. X., Chen, W.

Journal of Manufacturing Systems, 2024. Paper Link

A Digital Twin Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health Monitoring

Authors: Karkaria, V., Chen, J., Luey, C., Siuta, C., Lim, D., Radulescu, R., Chen, W.

arXiv preprint arXiv:2408.06220, 2024. Paper Link

A Machine Learning–Based Tire Life Prediction Framework for Increasing Life of Commercial Vehicle Tires

Authors: Karkaria, V., Chen, J., Siuta, C., Lim, D., Radulescu, R., Chen, W.

Journal of Mechanical Design, vol. 146, no. 2, 2024. Paper Link.

Tire Life Assessment for Increasing Re‐Manufacturing of Commercial Vehicle Tires

Authors: Karkaria, V., Chen, J., Siuta, C., Lim, D., Radulescu, R., Chen, W.

Technology Innovation for the Circular Economy: Recycling, Remanufacturing, Design, Systems Analysis and Logistics, 2024, pp. 599-612. Paper Link.

Digital twins for the designs of systems: a perspective

Authors: van Beek, Anton, Vispi Nevile Karkaria, and Wei Chen.

Structural and Multidisciplinary Optimization, vol. 66, no. 3, 2023, pp. 49. Paper Link.

Conference Papers

"A Computational Framework for Social Entrepreneurs to Determine Policies for Sustainable Development."

Authors: Karkaria, V., Das, A. K., Yadav, A., Sharma, A., Allen, J. K., Mistree, F.

Proceedings of the ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 3B: 47th Design Automation Conference (DAC). Virtual, Online. August 17–19, 2021. V03BT03A019. ASME. https://doi.org/10.1115/DETC2021-70827.

"Investigation of substitute jar materials for Laboratory-grade ball milling machine to process electrode materials for energy storage devices"

Authors: Shinde, S., Momin, T., Karkaria, V. N., Karandikar, P. B.

IOP Conference Series, Material Science and Engineering, pp. 12018, vol. 1206, doi:10.1088/1757-899x/1206/1/012018.

"Electrode electrolyte compatibility for superior performance of super-capacitor"

Authors: Godse, L. S., Karkaria, V. N., Bhalerao, M. J., Khatua, S., Karandikar, P. B.

International Conference on Power Electronics Applications and Technology in Present Energy Scenario, PETPES 2019 – Proceedings, Institute of Electrical and Electronics Engineers Inc, pp. 1-5, doi:10.1109/PETPES47060.2019.9003864.

"Sizing the connectors for super-capacitors"

Authors: Karkaria, V. N., Godse, L. S., Bhalerao, M.J., Dalal, R.

2019, International Conference On Electrical, Communication, Electronics, Instrumentation And Computing, Kanchipuram, Tamil Nadu, India, pp. 1-7.

"E-rickshaw present past and future with reference to current transportation in India"

Authors: Kokate, V. L., Bankar, D. S., Holmukhe, R. M., Karkaria, V. N., Karandikar, P. B.

International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering - (ICRIEECE), volume-01(01), pp-1–15.

"Review of technologies for making electric vehicles as main mode of transport"

Authors: Karkaria, V. N., Sarathchandran, V., Korgaonkar, P. R., Reddy, G. S. R., Mehta, S., Karandikar, P. B.

2018, International Conference On Advances in Communication and Computing Technology, ICACCT, Institute of Electrical and Electronics Engineers Inc, pp. 142–148, doi:10.1109/ICACCT.2018.8529591.

"Thermal dicky"

Authors: Karkaria, V. N., Korgaonkar, P. R, Karandikar, P. B.

2017, Conference at Institute of Engineers, Pune, Maharashtra, India, pp. 90-96.

"Innovative methods of ball milling to grind activated carbon as an electrode material for enhancing the performance of ultracapacitor"

Authors: Godse, L. S., Karkaria, V., Karandikar, P. B., Kulkarni, N. R.

International Conference on Energy, Communication, Data Analytics and Soft Computing, ICECDS 2017, pp. 2034–2041, Institute of Electrical and Electronics Engineers Inc, doi:10.1109/ICECDS.2017.8389807.