Real-Time Health Monitoring Using PINN + Hypernetwork
Project Overview
This project builds a Physics-Informed Neural Network with a hypernetwork to estimate internal temperature fields from live boundary data, enabling predictive maintenance and early fouling detection.
Tech Stack
Team
Mentors
- Rohit Singh
- Yash Jain
- Neha Ojha
Mentees
- Abhishek Mahato
- Diya Zacharia
- Rudransh Pandey
Problem Statement
Energy-intensive process industries lose substantial thermal energy, reducing efficiency and increasing carbon impact.
Objectives
- - Model waste heat streams in industrial processes
- - Design and simulate ORC in DWSIM
- - Run techno-economic analysis with payback and NPV metrics
Methodology
The project follows a structured implementation approach that includes Baseline process simulations in DWSIM, Working-fluid screening for ORC performance, Parametric optimization over key temperatures, and Economic evaluation using Excel/Matlab. These steps are executed iteratively to validate assumptions, improve performance, and ensure reliable delivery of the final solution.
Expected Outcome
By the end of this project, the team is expected to deliver Validated simulation with strong efficiency range, Optimal fluid recommendations, and Financial feasibility evaluation. Together, these outcomes reflect both technical feasibility and practical value for demos, evaluation, and future scaling.
Future Scope
- - Dynamic load-response modeling
- - Hybrid renewable integration
- - Life cycle environmental analysis