0000-0002-4177-8455 About
Abhijit Bhakte is a Prime Minister Research Fellow (PMRF) at the Indian Institute of Technology Madras. Currently, he works in the Intelligent Applications in Chemical Engineering (i-ACE) Laboratory under the supervision of Prof. Rajagopalan Srinivasan. With a robust academic foundation anchored by a B.Tech. in Chemical Engineering from SGGSIE&T, Nanded, Abhijit brings a wealth of knowledge and dedication to his research endeavors. Prior to his tenure at IIT Madras, he honed his skills as a Graduate Engineer Trainee at Navin Fluorine International Limited (NFIL), where he gained invaluable industry experience.
Abhijit's research interests span a diverse spectrum, focusing on cutting-edge areas such as Explainable Artificial Intelligence (XAI), Physics Informed Machine Learning, Process Monitoring, Soft Sensors, Fault Detection and Identification, and Decision Fusion. His current PhD work is centered on developing XAI techniques that enhance the interpretability of AI models while maintaining optimal performance. Moreover, he actively collaborates with industry partners, academia, and startups, notably contributing to building Green Aadhaar, an IIT Madras-based startup. With a proven track record evidenced by multiple journal and conference publications, as well as presentations at renowned international conferences like AIChE, ESCAPE, and PSE, Abhijit exemplifies a dynamic researcher committed to driving innovation at the intersection of artificial intelligence and chemical engineering.
Employment
Employment history is unavailable.
Education
Education history is unavailable.
Projects & Funding
Projects & funding information is unavailable.
Publications (8)
- Online parameter estimation and model maintenance using parameter-aware physics-informed neural network Save
- A novel hybrid neural network for modeling dynamic systems using physics-informed regularization Save
- Artificial intelligence and machine learning at various stages and scales of process systems engineering Save
- Explainable AI methodology for understanding fault detection results during Multi-Mode operations Save
- Adaptive Physics-Informed Neural Network for Prediction with Evolving Process Parameters Save
- Potential for Counterfactual Explanations to Support Digitalized Plant Operations Save
- Alarm-based explanations of process monitoring results from deep neural networks Save
- An explainable artificial intelligence based approach for interpretation of fault classification results from deep neural networks Save